Sparse Matrix for ECG Identification with Two-Lead Features

Directory of Open Access Journals (Sweden)

Kuo-Kun Tseng

2015-01-01

Full Text Available Electrocardiograph (ECG human identification has the potential to improve biometric security. However, improvements in ECG identification and feature extraction are required. Previous work has focused on single lead ECG signals. Our work proposes a new algorithm for human identification by mapping two-lead ECG signals onto a two-dimensional matrix then employing a sparse matrix method to process the matrix. And that is the first application of sparse matrix techniques for ECG identification. Moreover, the results of our experiments demonstrate the benefits of our approach over existing methods.

Enforced Sparse Non-Negative Matrix Factorization

Science.gov (United States)

2016-01-23

proposals quotas opec legislation revenue england ico iraq vote passenger yen producer iranian surplus Figure 4. Example NMF with and without sparsity...preprint arXiv:1007.0380, 2010. [22] A. Cichocki and P. Anh-Huy, “Fast local algorithms for large scale nonnegative matrix and tensor factorizations

Fast sparse matrix-vector multiplication by partitioning and reordering

NARCIS (Netherlands)

Yzelman, A.N.

2011-01-01

The thesis introduces a cache-oblivious method for the sparse matrix-vector (SpMV) multiplication, which is an important computational kernel in many applications. The method works by permuting rows and columns of the input matrix so that the resulting reordered matrix induces cache-friendly

A performance study of sparse Cholesky factorization on INTEL iPSC/860

Science.gov (United States)

Zubair, M.; Ghose, M.

1992-01-01

The problem of Cholesky factorization of a sparse matrix has been very well investigated on sequential machines. A number of efficient codes exist for factorizing large unstructured sparse matrices. However, there is a lack of such efficient codes on parallel machines in general, and distributed machines in particular. Some of the issues that are critical to the implementation of sparse Cholesky factorization on a distributed memory parallel machine are ordering, partitioning and mapping, load balancing, and ordering of various tasks within a processor. Here, we focus on the effect of various partitioning schemes on the performance of sparse Cholesky factorization on the Intel iPSC/860. Also, a new partitioning heuristic for structured as well as unstructured sparse matrices is proposed, and its performance is compared with other schemes.

Designing sparse sensing matrix for compressive sensing to reconstruct high resolution medical images

Directory of Open Access Journals (Sweden)

Vibha Tiwari

2015-12-01

Full Text Available Compressive sensing theory enables faithful reconstruction of signals, sparse in domain $ \\Psi $, at sampling rate lesser than Nyquist criterion, while using sampling or sensing matrix $ \\Phi $ which satisfies restricted isometric property. The role played by sensing matrix $ \\Phi $ and sparsity matrix $ \\Psi $ is vital in faithful reconstruction. If the sensing matrix is dense then it takes large storage space and leads to high computational cost. In this paper, effort is made to design sparse sensing matrix with least incurred computational cost while maintaining quality of reconstructed image. The design approach followed is based on sparse block circulant matrix (SBCM with few modifications. The other used sparse sensing matrix consists of 15 ones in each column. The medical images used are acquired from US, MRI and CT modalities. The image quality measurement parameters are used to compare the performance of reconstructed medical images using various sensing matrices. It is observed that, since Gram matrix of dictionary matrix ($ \\Phi \\Psi \\mathrm{} $ is closed to identity matrix in case of proposed modified SBCM, therefore, it helps to reconstruct the medical images of very good quality.

Multi scales based sparse matrix spectral clustering image segmentation

Science.gov (United States)

Liu, Zhongmin; Chen, Zhicai; Li, Zhanming; Hu, Wenjin

2018-04-01

In image segmentation, spectral clustering algorithms have to adopt the appropriate scaling parameter to calculate the similarity matrix between the pixels, which may have a great impact on the clustering result. Moreover, when the number of data instance is large, computational complexity and memory use of the algorithm will greatly increase. To solve these two problems, we proposed a new spectral clustering image segmentation algorithm based on multi scales and sparse matrix. We devised a new feature extraction method at first, then extracted the features of image on different scales, at last, using the feature information to construct sparse similarity matrix which can improve the operation efficiency. Compared with traditional spectral clustering algorithm, image segmentation experimental results show our algorithm have better degree of accuracy and robustness.

Pulse-Width-Modulation of Neutral-Point-Clamped Sparse Matrix Converter

DEFF Research Database (Denmark)

Loh, P.C.; Blaabjerg, Frede; Gao, F.

2007-01-01

input current and output voltage can be achieved with minimized rectification switching loss, rendering the sparse matrix converter as a competitive choice for interfacing the utility grid to (e.g.) defense facilities that require a different frequency supply. As an improvement, sparse matrix converter...... with improved waveform quality. Performances and practicalities of the designed schemes are verified in simulation and experimentally using an implemented laboratory prototype with some representative results captured and presented in the paper....

Design Patterns for Sparse-Matrix Computations on Hybrid CPU/GPU Platforms

Directory of Open Access Journals (Sweden)

Valeria Cardellini

2014-01-01

Full Text Available We apply object-oriented software design patterns to develop code for scientific software involving sparse matrices. Design patterns arise when multiple independent developments produce similar designs which converge onto a generic solution. We demonstrate how to use design patterns to implement an interface for sparse matrix computations on NVIDIA GPUs starting from PSBLAS, an existing sparse matrix library, and from existing sets of GPU kernels for sparse matrices. We also compare the throughput of the PSBLAS sparse matrix–vector multiplication on two platforms exploiting the GPU with that obtained by a CPU-only PSBLAS implementation. Our experiments exhibit encouraging results regarding the comparison between CPU and GPU executions in double precision, obtaining a speedup of up to 35.35 on NVIDIA GTX 285 with respect to AMD Athlon 7750, and up to 10.15 on NVIDIA Tesla C2050 with respect to Intel Xeon X5650.

Vector sparse representation of color image using quaternion matrix analysis.

Science.gov (United States)

Xu, Yi; Yu, Licheng; Xu, Hongteng; Zhang, Hao; Nguyen, Truong

2015-04-01

Traditional sparse image models treat color image pixel as a scalar, which represents color channels separately or concatenate color channels as a monochrome image. In this paper, we propose a vector sparse representation model for color images using quaternion matrix analysis. As a new tool for color image representation, its potential applications in several image-processing tasks are presented, including color image reconstruction, denoising, inpainting, and super-resolution. The proposed model represents the color image as a quaternion matrix, where a quaternion-based dictionary learning algorithm is presented using the K-quaternion singular value decomposition (QSVD) (generalized K-means clustering for QSVD) method. It conducts the sparse basis selection in quaternion space, which uniformly transforms the channel images to an orthogonal color space. In this new color space, it is significant that the inherent color structures can be completely preserved during vector reconstruction. Moreover, the proposed sparse model is more efficient comparing with the current sparse models for image restoration tasks due to lower redundancy between the atoms of different color channels. The experimental results demonstrate that the proposed sparse image model avoids the hue bias issue successfully and shows its potential as a general and powerful tool in color image analysis and processing domain.

Optimizing Sparse Matrix-Multiple Vectors Multiplication for Nuclear Configuration Interaction Calculations

Energy Technology Data Exchange (ETDEWEB)

Aktulga, Hasan Metin [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Buluc, Aydin [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Williams, Samuel [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Yang, Chao [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

2014-08-14

Obtaining highly accurate predictions on the properties of light atomic nuclei using the configuration interaction (CI) approach requires computing a few extremal Eigen pairs of the many-body nuclear Hamiltonian matrix. In the Many-body Fermion Dynamics for nuclei (MFDn) code, a block Eigen solver is used for this purpose. Due to the large size of the sparse matrices involved, a significant fraction of the time spent on the Eigen value computations is associated with the multiplication of a sparse matrix (and the transpose of that matrix) with multiple vectors (SpMM and SpMM-T). Existing implementations of SpMM and SpMM-T significantly underperform expectations. Thus, in this paper, we present and analyze optimized implementations of SpMM and SpMM-T. We base our implementation on the compressed sparse blocks (CSB) matrix format and target systems with multi-core architectures. We develop a performance model that allows us to understand and estimate the performance characteristics of our SpMM kernel implementations, and demonstrate the efficiency of our implementation on a series of real-world matrices extracted from MFDn. In particular, we obtain 3-4 speedup on the requisite operations over good implementations based on the commonly used compressed sparse row (CSR) matrix format. The improvements in the SpMM kernel suggest we may attain roughly a 40% speed up in the overall execution time of the block Eigen solver used in MFDn.

New sparse matrix solver in the KIKO3D 3-dimensional reactor dynamics code

International Nuclear Information System (INIS)

Panka, I.; Kereszturi, A.; Hegedus, C.

2005-01-01

The goal of this paper is to present a more effective method Bi-CGSTAB for accelerating the large sparse matrix equation solution in the KIKO3D code. This equation system is obtained by using the factorization of the improved quasi static (IQS) method for the time dependent nodal kinetic equations. In the old methodology standard large sparse matrix techniques were considered, where Gauss-Seidel preconditioning and a GMRES-type solver were applied. The validation of KIKO3D using Bi-CGSTAB has been performed by solving of a VVER-1000 kinetic benchmark problem. Additionally, the convergence characteristics were investigated in given macro time steps of Control Rod Ejection transients. The results have been obtained by the old GMRES and new Bi-CGSTAB methods are compared. (author)

Sparse and smooth canonical correlation analysis through rank-1 matrix approximation

Science.gov (United States)

Aïssa-El-Bey, Abdeldjalil; Seghouane, Abd-Krim

2017-12-01

Canonical correlation analysis (CCA) is a well-known technique used to characterize the relationship between two sets of multidimensional variables by finding linear combinations of variables with maximal correlation. Sparse CCA and smooth or regularized CCA are two widely used variants of CCA because of the improved interpretability of the former and the better performance of the later. So far, the cross-matrix product of the two sets of multidimensional variables has been widely used for the derivation of these variants. In this paper, two new algorithms for sparse CCA and smooth CCA are proposed. These algorithms differ from the existing ones in their derivation which is based on penalized rank-1 matrix approximation and the orthogonal projectors onto the space spanned by the two sets of multidimensional variables instead of the simple cross-matrix product. The performance and effectiveness of the proposed algorithms are tested on simulated experiments. On these results, it can be observed that they outperform the state of the art sparse CCA algorithms.

Better Size Estimation for Sparse Matrix Products

DEFF Research Database (Denmark)

Amossen, Rasmus Resen; Campagna, Andrea; Pagh, Rasmus

2010-01-01

We consider the problem of doing fast and reliable estimation of the number of non-zero entries in a sparse Boolean matrix product. Let n denote the total number of non-zero entries in the input matrices. We show how to compute a 1 ± ε approximation (with small probability of error) in expected t...

HIGH DIMENSIONAL COVARIANCE MATRIX ESTIMATION IN APPROXIMATE FACTOR MODELS.

Science.gov (United States)

Fan, Jianqing; Liao, Yuan; Mincheva, Martina

2011-01-01

The variance covariance matrix plays a central role in the inferential theories of high dimensional factor models in finance and economics. Popular regularization methods of directly exploiting sparsity are not directly applicable to many financial problems. Classical methods of estimating the covariance matrices are based on the strict factor models, assuming independent idiosyncratic components. This assumption, however, is restrictive in practical applications. By assuming sparse error covariance matrix, we allow the presence of the cross-sectional correlation even after taking out common factors, and it enables us to combine the merits of both methods. We estimate the sparse covariance using the adaptive thresholding technique as in Cai and Liu (2011), taking into account the fact that direct observations of the idiosyncratic components are unavailable. The impact of high dimensionality on the covariance matrix estimation based on the factor structure is then studied.

Ab initio nuclear structure - the large sparse matrix eigenvalue problem

Energy Technology Data Exchange (ETDEWEB)

Vary, James P; Maris, Pieter [Department of Physics, Iowa State University, Ames, IA, 50011 (United States); Ng, Esmond; Yang, Chao [Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720 (United States); Sosonkina, Masha, E-mail: jvary@iastate.ed [Scalable Computing Laboratory, Ames Laboratory, Iowa State University, Ames, IA, 50011 (United States)

2009-07-01

The structure and reactions of light nuclei represent fundamental and formidable challenges for microscopic theory based on realistic strong interaction potentials. Several ab initio methods have now emerged that provide nearly exact solutions for some nuclear properties. The ab initio no core shell model (NCSM) and the no core full configuration (NCFC) method, frame this quantum many-particle problem as a large sparse matrix eigenvalue problem where one evaluates the Hamiltonian matrix in a basis space consisting of many-fermion Slater determinants and then solves for a set of the lowest eigenvalues and their associated eigenvectors. The resulting eigenvectors are employed to evaluate a set of experimental quantities to test the underlying potential. For fundamental problems of interest, the matrix dimension often exceeds 10{sup 10} and the number of nonzero matrix elements may saturate available storage on present-day leadership class facilities. We survey recent results and advances in solving this large sparse matrix eigenvalue problem. We also outline the challenges that lie ahead for achieving further breakthroughs in fundamental nuclear theory using these ab initio approaches.

Ab initio nuclear structure - the large sparse matrix eigenvalue problem

International Nuclear Information System (INIS)

Vary, James P; Maris, Pieter; Ng, Esmond; Yang, Chao; Sosonkina, Masha

2009-01-01

The structure and reactions of light nuclei represent fundamental and formidable challenges for microscopic theory based on realistic strong interaction potentials. Several ab initio methods have now emerged that provide nearly exact solutions for some nuclear properties. The ab initio no core shell model (NCSM) and the no core full configuration (NCFC) method, frame this quantum many-particle problem as a large sparse matrix eigenvalue problem where one evaluates the Hamiltonian matrix in a basis space consisting of many-fermion Slater determinants and then solves for a set of the lowest eigenvalues and their associated eigenvectors. The resulting eigenvectors are employed to evaluate a set of experimental quantities to test the underlying potential. For fundamental problems of interest, the matrix dimension often exceeds 10 10 and the number of nonzero matrix elements may saturate available storage on present-day leadership class facilities. We survey recent results and advances in solving this large sparse matrix eigenvalue problem. We also outline the challenges that lie ahead for achieving further breakthroughs in fundamental nuclear theory using these ab initio approaches.

Encoding of rat working memory by power of multi-channel local field potentials via sparse non-negative matrix factorization

Institute of Scientific and Technical Information of China (English)

Xu Liu; Tiao-Tiao Liu; Wen-Wen Bai; Hu Yi; Shuang-Yan Li; Xin Tian

2013-01-01

Working memory plays an important role in human cognition.This study investigated how working memory was encoded by the power of multi-channel local field potentials (LFPs) based on sparse nonnegative matrix factorization (SNMF).SNMF was used to extract features from LFPs recorded from the prefrontal cortex of four Sprague-Dawley rats during a memory task in a Y maze,with 10 trials for each rat.Then the power-increased LFP components were selected as working memory-related features and the other components were removed.After that,the inverse operation of SNMF was used to study the encoding of working memory in the timefrequency domain.We demonstrated that theta and gamma power increased significantly during the working memory task.The results suggested that postsynaptic activity was simulated well by the sparse activity model.The theta and gamma bands were meaningful for encoding working memory.

On affine non-negative matrix factorization

DEFF Research Database (Denmark)

Laurberg, Hans; Hansen, Lars Kai

2007-01-01

We generalize the non-negative matrix factorization (NMF) generative model to incorporate an explicit offset. Multiplicative estimation algorithms are provided for the resulting sparse affine NMF model. We show that the affine model has improved uniqueness properties and leads to more accurate id...

Implementation of hierarchical clustering using k-mer sparse matrix to analyze MERS-CoV genetic relationship

Science.gov (United States)

Bustamam, A.; Ulul, E. D.; Hura, H. F. A.; Siswantining, T.

2017-07-01

Hierarchical clustering is one of effective methods in creating a phylogenetic tree based on the distance matrix between DNA (deoxyribonucleic acid) sequences. One of the well-known methods to calculate the distance matrix is k-mer method. Generally, k-mer is more efficient than some distance matrix calculation techniques. The steps of k-mer method are started from creating k-mer sparse matrix, and followed by creating k-mer singular value vectors. The last step is computing the distance amongst vectors. In this paper, we analyze the sequences of MERS-CoV (Middle East Respiratory Syndrome - Coronavirus) DNA by implementing hierarchical clustering using k-mer sparse matrix in order to perform the phylogenetic analysis. Our results show that the ancestor of our MERS-CoV is coming from Egypt. Moreover, we found that the MERS-CoV infection that occurs in one country may not necessarily come from the same country of origin. This suggests that the process of MERS-CoV mutation might not only be influenced by geographical factor.

Efficient MATLAB computations with sparse and factored tensors.

Energy Technology Data Exchange (ETDEWEB)

Bader, Brett William; Kolda, Tamara Gibson (Sandia National Lab, Livermore, CA)

2006-12-01

In this paper, the term tensor refers simply to a multidimensional or N-way array, and we consider how specially structured tensors allow for efficient storage and computation. First, we study sparse tensors, which have the property that the vast majority of the elements are zero. We propose storing sparse tensors using coordinate format and describe the computational efficiency of this scheme for various mathematical operations, including those typical to tensor decomposition algorithms. Second, we study factored tensors, which have the property that they can be assembled from more basic components. We consider two specific types: a Tucker tensor can be expressed as the product of a core tensor (which itself may be dense, sparse, or factored) and a matrix along each mode, and a Kruskal tensor can be expressed as the sum of rank-1 tensors. We are interested in the case where the storage of the components is less than the storage of the full tensor, and we demonstrate that many elementary operations can be computed using only the components. All of the efficiencies described in this paper are implemented in the Tensor Toolbox for MATLAB.

SparseM: A Sparse Matrix Package for R *

Directory of Open Access Journals (Sweden)

Roger Koenker

2003-02-01

Full Text Available SparseM provides some basic R functionality for linear algebra with sparse matrices. Use of the package is illustrated by a family of linear model fitting functions that implement least squares methods for problems with sparse design matrices. Significant performance improvements in memory utilization and computational speed are possible for applications involving large sparse matrices.

Improved success of sparse matrix protein crystallization screening with heterogeneous nucleating agents.

Directory of Open Access Journals (Sweden)

Anil S Thakur

2007-10-01

Full Text Available Crystallization is a major bottleneck in the process of macromolecular structure determination by X-ray crystallography. Successful crystallization requires the formation of nuclei and their subsequent growth to crystals of suitable size. Crystal growth generally occurs spontaneously in a supersaturated solution as a result of homogenous nucleation. However, in a typical sparse matrix screening experiment, precipitant and protein concentration are not sampled extensively, and supersaturation conditions suitable for nucleation are often missed.We tested the effect of nine potential heterogenous nucleating agents on crystallization of ten test proteins in a sparse matrix screen. Several nucleating agents induced crystal formation under conditions where no crystallization occurred in the absence of the nucleating agent. Four nucleating agents: dried seaweed; horse hair; cellulose and hydroxyapatite, had a considerable overall positive effect on crystallization success. This effect was further enhanced when these nucleating agents were used in combination with each other.Our results suggest that the addition of heterogeneous nucleating agents increases the chances of crystal formation when using sparse matrix screens.

Efficient diagonalization of the sparse matrices produced within the framework of the UK R-matrix molecular codes

Science.gov (United States)

Galiatsatos, P. G.; Tennyson, J.

2012-11-01

The most time consuming step within the framework of the UK R-matrix molecular codes is that of the diagonalization of the inner region Hamiltonian matrix (IRHM). Here we present the method that we follow to speed up this step. We use shared memory machines (SMM), distributed memory machines (DMM), the OpenMP directive based parallel language, the MPI function based parallel language, the sparse matrix diagonalizers ARPACK and PARPACK, a variation for real symmetric matrices of the official coordinate sparse matrix format and finally a parallel sparse matrix-vector product (PSMV). The efficient application of the previous techniques rely on two important facts: the sparsity of the matrix is large enough (more than 98%) and in order to get back converged results we need a small only part of the matrix spectrum.

Dissecting high-dimensional phenotypes with bayesian sparse factor analysis of genetic covariance matrices.

Science.gov (United States)

Runcie, Daniel E; Mukherjee, Sayan

2013-07-01

Quantitative genetic studies that model complex, multivariate phenotypes are important for both evolutionary prediction and artificial selection. For example, changes in gene expression can provide insight into developmental and physiological mechanisms that link genotype and phenotype. However, classical analytical techniques are poorly suited to quantitative genetic studies of gene expression where the number of traits assayed per individual can reach many thousand. Here, we derive a Bayesian genetic sparse factor model for estimating the genetic covariance matrix (G-matrix) of high-dimensional traits, such as gene expression, in a mixed-effects model. The key idea of our model is that we need consider only G-matrices that are biologically plausible. An organism's entire phenotype is the result of processes that are modular and have limited complexity. This implies that the G-matrix will be highly structured. In particular, we assume that a limited number of intermediate traits (or factors, e.g., variations in development or physiology) control the variation in the high-dimensional phenotype, and that each of these intermediate traits is sparse - affecting only a few observed traits. The advantages of this approach are twofold. First, sparse factors are interpretable and provide biological insight into mechanisms underlying the genetic architecture. Second, enforcing sparsity helps prevent sampling errors from swamping out the true signal in high-dimensional data. We demonstrate the advantages of our model on simulated data and in an analysis of a published Drosophila melanogaster gene expression data set.

Sparse Matrix-Vector Multiplication on Multicore and Accelerators

Energy Technology Data Exchange (ETDEWEB)

Williams, Samuel W. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Bell, Nathan [NVIDIA Research, Santa Clara, CA (United States); Choi, Jee Whan [Georgia Inst. of Technology, Atlanta, GA (United States); Garland, Michael [NVIDIA Research, Santa Clara, CA (United States); Oliker, Leonid [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Vuduc, Richard [Georgia Inst. of Technology, Atlanta, GA (United States)

2010-12-07

This chapter consolidates recent work on the development of high performance multicore and accelerator-based implementations of sparse matrix-vector multiplication (SpMV). As an object of study, SpMV is an interesting computation for two key reasons. First, it appears widely in applications in scientific and engineering computing, financial and economic modeling, and information retrieval, among others, and is therefore of great practical interest. Secondly, it is both simple to describe but challenging to implement well, since its performance is limited by a variety of factors, including low computational intensity, potentially highly irregular memory access behavior, and a strong input dependence that be known only at run time. Thus, we believe SpMV is both practically important and provides important insights for understanding the algorithmic and implementation principles necessary to making effective use of state-of-the-art systems.

Sparse subspace clustering for data with missing entries and high-rank matrix completion.

Science.gov (United States)

Fan, Jicong; Chow, Tommy W S

2017-09-01

Many methods have recently been proposed for subspace clustering, but they are often unable to handle incomplete data because of missing entries. Using matrix completion methods to recover missing entries is a common way to solve the problem. Conventional matrix completion methods require that the matrix should be of low-rank intrinsically, but most matrices are of high-rank or even full-rank in practice, especially when the number of subspaces is large. In this paper, a new method called Sparse Representation with Missing Entries and Matrix Completion is proposed to solve the problems of incomplete-data subspace clustering and high-rank matrix completion. The proposed algorithm alternately computes the matrix of sparse representation coefficients and recovers the missing entries of a data matrix. The proposed algorithm recovers missing entries through minimizing the representation coefficients, representation errors, and matrix rank. Thorough experimental study and comparative analysis based on synthetic data and natural images were conducted. The presented results demonstrate that the proposed algorithm is more effective in subspace clustering and matrix completion compared with other existing methods. Copyright © 2017 Elsevier Ltd. All rights reserved.

Fast convolutional sparse coding using matrix inversion lemma

Czech Academy of Sciences Publication Activity Database

Šorel, Michal; Šroubek, Filip

2016-01-01

Roč. 55, č. 1 (2016), s. 44-51 ISSN 1051-2004 R&D Projects: GA ČR GA13-29225S Institutional support: RVO:67985556 Keywords : Convolutional sparse coding * Feature learning * Deconvolution networks * Shift-invariant sparse coding Subject RIV: JD - Computer Applications, Robotics Impact factor: 2.337, year: 2016 http://library.utia.cas.cz/separaty/2016/ZOI/sorel-0459332.pdf

Sparse Covariance Matrix Estimation by DCA-Based Algorithms.

Science.gov (United States)

Phan, Duy Nhat; Le Thi, Hoai An; Dinh, Tao Pham

2017-11-01

This letter proposes a novel approach using the [Formula: see text]-norm regularization for the sparse covariance matrix estimation (SCME) problem. The objective function of SCME problem is composed of a nonconvex part and the [Formula: see text] term, which is discontinuous and difficult to tackle. Appropriate DC (difference of convex functions) approximations of [Formula: see text]-norm are used that result in approximation SCME problems that are still nonconvex. DC programming and DCA (DC algorithm), powerful tools in nonconvex programming framework, are investigated. Two DC formulations are proposed and corresponding DCA schemes developed. Two applications of the SCME problem that are considered are classification via sparse quadratic discriminant analysis and portfolio optimization. A careful empirical experiment is performed through simulated and real data sets to study the performance of the proposed algorithms. Numerical results showed their efficiency and their superiority compared with seven state-of-the-art methods.

Sparse matrix-vector multiplication on GPGPU clusters: A new storage format and a scalable implementation

OpenAIRE

Kreutzer, Moritz; Hager, Georg; Wellein, Gerhard; Fehske, Holger; Basermann, Achim; Bishop, Alan R.

2011-01-01

Sparse matrix-vector multiplication (spMVM) is the dominant operation in many sparse solvers. We investigate performance properties of spMVM with matrices of various sparsity patterns on the nVidia “Fermi” class of GPGPUs. A new “padded jagged diagonals storage” (pJDS) format is proposed which may substantially reduce the memory overhead intrinsic to the widespread ELLPACK-R scheme while making no assumptions about the matrix structure. In our test scenarios the pJDS format cuts the ...

Parallelized preconditioned model building algorithm for matrix factorization

OpenAIRE

Kaya, Kamer; Birbil, İlker; Birbil, Ilker; Öztürk, Mehmet Kaan; Ozturk, Mehmet Kaan; Gohari, Amir

2017-01-01

Matrix factorization is a common task underlying several machine learning applications such as recommender systems, topic modeling, or compressed sensing. Given a large and possibly sparse matrix A, we seek two smaller matrices W and H such that their product is as close to A as possible. The objective is minimizing the sum of square errors in the approximation. Typically such problems involve hundreds of thousands of unknowns, so an optimizer must be exceptionally efficient. In this study, a...

Incremental Nonnegative Matrix Factorization for Face Recognition

Directory of Open Access Journals (Sweden)

Wen-Sheng Chen

2008-01-01

Full Text Available Nonnegative matrix factorization (NMF is a promising approach for local feature extraction in face recognition tasks. However, there are two major drawbacks in almost all existing NMF-based methods. One shortcoming is that the computational cost is expensive for large matrix decomposition. The other is that it must conduct repetitive learning, when the training samples or classes are updated. To overcome these two limitations, this paper proposes a novel incremental nonnegative matrix factorization (INMF for face representation and recognition. The proposed INMF approach is based on a novel constraint criterion and our previous block strategy. It thus has some good properties, such as low computational complexity, sparse coefficient matrix. Also, the coefficient column vectors between different classes are orthogonal. In particular, it can be applied to incremental learning. Two face databases, namely FERET and CMU PIE face databases, are selected for evaluation. Compared with PCA and some state-of-the-art NMF-based methods, our INMF approach gives the best performance.

Library designs for generic C++ sparse matrix computations of iterative methods

Energy Technology Data Exchange (ETDEWEB)

Pozo, R.

1996-12-31

A new library design is presented for generic sparse matrix C++ objects for use in iterative algorithms and preconditioners. This design extends previous work on C++ numerical libraries by providing a framework in which efficient algorithms can be written *independent* of the matrix layout or format. That is, rather than supporting different codes for each (element type) / (matrix format) combination, only one version of the algorithm need be maintained. This not only reduces the effort for library developers, but also simplifies the calling interface seen by library users. Furthermore, the underlying matrix library can be naturally extended to support user-defined objects, such as hierarchical block-structured matrices, or application-specific preconditioners. Utilizing optimized kernels whenever possible, the resulting performance of such framework can be shown to be competitive with optimized Fortran programs.

MIMO-OFDM Chirp Waveform Diversity Design and Implementation Based on Sparse Matrix and Correlation Optimization

Directory of Open Access Journals (Sweden)

Wang Wen-qin

2015-02-01

Full Text Available The waveforms used in Multiple-Input Multiple-Output (MIMO Synthetic Aperture Radar (SAR should have a large time-bandwidth product and good ambiguity function performance. A scheme to design multiple orthogonal MIMO SAR Orthogonal Frequency Division Multiplexing (OFDM chirp waveforms by combinational sparse matrix and correlation optimization is proposed. First, the problem of MIMO SAR waveform design amounts to the associated design of hopping frequency and amplitudes. Then a iterative exhaustive search algorithm is adopted to optimally design the code matrix with the constraints minimizing the block correlation coefficient of sparse matrix and the sum of cross-correlation peaks. And the amplitudes matrix are adaptively designed by minimizing the cross-correlation peaks with the genetic algorithm. Additionally, the impacts of waveform number, hopping frequency interval and selectable frequency index are also analyzed. The simulation results verify the proposed scheme can design multiple orthogonal large time-bandwidth product OFDM chirp waveforms with low cross-correlation peak and sidelobes and it improves ambiguity performance.

Nonnegative Matrix Factorization with Rank Regularization and Hard Constraint.

Science.gov (United States)

Shang, Ronghua; Liu, Chiyang; Meng, Yang; Jiao, Licheng; Stolkin, Rustam

2017-09-01

Nonnegative matrix factorization (NMF) is well known to be an effective tool for dimensionality reduction in problems involving big data. For this reason, it frequently appears in many areas of scientific and engineering literature. This letter proposes a novel semisupervised NMF algorithm for overcoming a variety of problems associated with NMF algorithms, including poor use of prior information, negative impact on manifold structure of the sparse constraint, and inaccurate graph construction. Our proposed algorithm, nonnegative matrix factorization with rank regularization and hard constraint (NMFRC), incorporates label information into data representation as a hard constraint, which makes full use of prior information. NMFRC also measures pairwise similarity according to geodesic distance rather than Euclidean distance. This results in more accurate measurement of pairwise relationships, resulting in more effective manifold information. Furthermore, NMFRC adopts rank constraint instead of norm constraints for regularization to balance the sparseness and smoothness of data. In this way, the new data representation is more representative and has better interpretability. Experiments on real data sets suggest that NMFRC outperforms four other state-of-the-art algorithms in terms of clustering accuracy.

A Novel CSR-Based Sparse Matrix-Vector Multiplication on GPUs

Directory of Open Access Journals (Sweden)

Guixia He

2016-01-01

Full Text Available Sparse matrix-vector multiplication (SpMV is an important operation in scientific computations. Compressed sparse row (CSR is the most frequently used format to store sparse matrices. However, CSR-based SpMVs on graphic processing units (GPUs, for example, CSR-scalar and CSR-vector, usually have poor performance due to irregular memory access patterns. This motivates us to propose a perfect CSR-based SpMV on the GPU that is called PCSR. PCSR involves two kernels and accesses CSR arrays in a fully coalesced manner by introducing a middle array, which greatly alleviates the deficiencies of CSR-scalar (rare coalescing and CSR-vector (partial coalescing. Test results on a single C2050 GPU show that PCSR fully outperforms CSR-scalar, CSR-vector, and CSRMV and HYBMV in the vendor-tuned CUSPARSE library and is comparable with a most recently proposed CSR-based algorithm, CSR-Adaptive. Furthermore, we extend PCSR on a single GPU to multiple GPUs. Experimental results on four C2050 GPUs show that no matter whether the communication between GPUs is considered or not PCSR on multiple GPUs achieves good performance and has high parallel efficiency.

Performance optimization of Sparse Matrix-Vector Multiplication for multi-component PDE-based applications using GPUs

KAUST Repository

Abdelfattah, Ahmad

2016-05-23

Simulations of many multi-component PDE-based applications, such as petroleum reservoirs or reacting flows, are dominated by the solution, on each time step and within each Newton step, of large sparse linear systems. The standard solver is a preconditioned Krylov method. Along with application of the preconditioner, memory-bound Sparse Matrix-Vector Multiplication (SpMV) is the most time-consuming operation in such solvers. Multi-species models produce Jacobians with a dense block structure, where the block size can be as large as a few dozen. Failing to exploit this dense block structure vastly underutilizes hardware capable of delivering high performance on dense BLAS operations. This paper presents a GPU-accelerated SpMV kernel for block-sparse matrices. Dense matrix-vector multiplications within the sparse-block structure leverage optimization techniques from the KBLAS library, a high performance library for dense BLAS kernels. The design ideas of KBLAS can be applied to block-sparse matrices. Furthermore, a technique is proposed to balance the workload among thread blocks when there are large variations in the lengths of nonzero rows. Multi-GPU performance is highlighted. The proposed SpMV kernel outperforms existing state-of-the-art implementations using matrices with real structures from different applications. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Performance optimization of Sparse Matrix-Vector Multiplication for multi-component PDE-based applications using GPUs

KAUST Repository

Abdelfattah, Ahmad; Ltaief, Hatem; Keyes, David E.; Dongarra, Jack

2016-01-01

Simulations of many multi-component PDE-based applications, such as petroleum reservoirs or reacting flows, are dominated by the solution, on each time step and within each Newton step, of large sparse linear systems. The standard solver is a preconditioned Krylov method. Along with application of the preconditioner, memory-bound Sparse Matrix-Vector Multiplication (SpMV) is the most time-consuming operation in such solvers. Multi-species models produce Jacobians with a dense block structure, where the block size can be as large as a few dozen. Failing to exploit this dense block structure vastly underutilizes hardware capable of delivering high performance on dense BLAS operations. This paper presents a GPU-accelerated SpMV kernel for block-sparse matrices. Dense matrix-vector multiplications within the sparse-block structure leverage optimization techniques from the KBLAS library, a high performance library for dense BLAS kernels. The design ideas of KBLAS can be applied to block-sparse matrices. Furthermore, a technique is proposed to balance the workload among thread blocks when there are large variations in the lengths of nonzero rows. Multi-GPU performance is highlighted. The proposed SpMV kernel outperforms existing state-of-the-art implementations using matrices with real structures from different applications. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Improving residue-residue contact prediction via low-rank and sparse decomposition of residue correlation matrix.

Science.gov (United States)

Zhang, Haicang; Gao, Yujuan; Deng, Minghua; Wang, Chao; Zhu, Jianwei; Li, Shuai Cheng; Zheng, Wei-Mou; Bu, Dongbo

2016-03-25

Strategies for correlation analysis in protein contact prediction often encounter two challenges, namely, the indirect coupling among residues, and the background correlations mainly caused by phylogenetic biases. While various studies have been conducted on how to disentangle indirect coupling, the removal of background correlations still remains unresolved. Here, we present an approach for removing background correlations via low-rank and sparse decomposition (LRS) of a residue correlation matrix. The correlation matrix can be constructed using either local inference strategies (e.g., mutual information, or MI) or global inference strategies (e.g., direct coupling analysis, or DCA). In our approach, a correlation matrix was decomposed into two components, i.e., a low-rank component representing background correlations, and a sparse component representing true correlations. Finally the residue contacts were inferred from the sparse component of correlation matrix. We trained our LRS-based method on the PSICOV dataset, and tested it on both GREMLIN and CASP11 datasets. Our experimental results suggested that LRS significantly improves the contact prediction precision. For example, when equipped with the LRS technique, the prediction precision of MI and mfDCA increased from 0.25 to 0.67 and from 0.58 to 0.70, respectively (Top L/10 predicted contacts, sequence separation: 5 AA, dataset: GREMLIN). In addition, our LRS technique also consistently outperforms the popular denoising technique APC (average product correction), on both local (MI_LRS: 0.67 vs MI_APC: 0.34) and global measures (mfDCA_LRS: 0.70 vs mfDCA_APC: 0.67). Interestingly, we found out that when equipped with our LRS technique, local inference strategies performed in a comparable manner to that of global inference strategies, implying that the application of LRS technique narrowed down the performance gap between local and global inference strategies. Overall, our LRS technique greatly facilitates

Reducing computational costs in large scale 3D EIT by using a sparse Jacobian matrix with block-wise CGLS reconstruction

International Nuclear Information System (INIS)

Yang, C L; Wei, H Y; Soleimani, M; Adler, A

2013-01-01

Electrical impedance tomography (EIT) is a fast and cost-effective technique to provide a tomographic conductivity image of a subject from boundary current–voltage data. This paper proposes a time and memory efficient method for solving a large scale 3D EIT inverse problem using a parallel conjugate gradient (CG) algorithm. The 3D EIT system with a large number of measurement data can produce a large size of Jacobian matrix; this could cause difficulties in computer storage and the inversion process. One of challenges in 3D EIT is to decrease the reconstruction time and memory usage, at the same time retaining the image quality. Firstly, a sparse matrix reduction technique is proposed using thresholding to set very small values of the Jacobian matrix to zero. By adjusting the Jacobian matrix into a sparse format, the element with zeros would be eliminated, which results in a saving of memory requirement. Secondly, a block-wise CG method for parallel reconstruction has been developed. The proposed method has been tested using simulated data as well as experimental test samples. Sparse Jacobian with a block-wise CG enables the large scale EIT problem to be solved efficiently. Image quality measures are presented to quantify the effect of sparse matrix reduction in reconstruction results. (paper)

Reducing computational costs in large scale 3D EIT by using a sparse Jacobian matrix with block-wise CGLS reconstruction.

Science.gov (United States)

Yang, C L; Wei, H Y; Adler, A; Soleimani, M

2013-06-01

Electrical impedance tomography (EIT) is a fast and cost-effective technique to provide a tomographic conductivity image of a subject from boundary current-voltage data. This paper proposes a time and memory efficient method for solving a large scale 3D EIT inverse problem using a parallel conjugate gradient (CG) algorithm. The 3D EIT system with a large number of measurement data can produce a large size of Jacobian matrix; this could cause difficulties in computer storage and the inversion process. One of challenges in 3D EIT is to decrease the reconstruction time and memory usage, at the same time retaining the image quality. Firstly, a sparse matrix reduction technique is proposed using thresholding to set very small values of the Jacobian matrix to zero. By adjusting the Jacobian matrix into a sparse format, the element with zeros would be eliminated, which results in a saving of memory requirement. Secondly, a block-wise CG method for parallel reconstruction has been developed. The proposed method has been tested using simulated data as well as experimental test samples. Sparse Jacobian with a block-wise CG enables the large scale EIT problem to be solved efficiently. Image quality measures are presented to quantify the effect of sparse matrix reduction in reconstruction results.

Algorithms for sparse, symmetric, definite quadratic lambda-matrix eigenproblems

International Nuclear Information System (INIS)

Scott, D.S.; Ward, R.C.

1981-01-01

Methods are presented for computing eigenpairs of the quadratic lambda-matrix, M lambda 2 + C lambda + K, where M, C, and K are large and sparse, and have special symmetry-type properties. These properties are sufficient to insure that all the eigenvalues are real and that theory analogous to the standard symmetric eigenproblem exists. The methods employ some standard techniques such as partial tri-diagonalization via the Lanczos Method and subsequent eigenpair calculation, shift-and- invert strategy and subspace iteration. The methods also employ some new techniques such as Rayleigh-Ritz quadratic roots and the inertia of symmetric, definite, quadratic lambda-matrices

An Extended-Tag-Induced Matrix Factorization Technique for Recommender Systems

Directory of Open Access Journals (Sweden)

Huirui Han

2018-06-01

Full Text Available Social tag information has been used by recommender systems to handle the problem of data sparsity. Recently, the relationships between users/items and tags are considered by most tag-induced recommendation methods. However, sparse tag information is challenging to most existing methods. In this paper, we propose an Extended-Tag-Induced Matrix Factorization technique for recommender systems, which exploits correlations among tags derived by co-occurrence of tags to improve the performance of recommender systems, even in the case of sparse tag information. The proposed method integrates coupled similarity between tags, which is calculated by the co-occurrences of tags in the same items, to extend each item’s tags. Finally, item similarity based on extended tags is utilized as an item relationship regularization term to constrain the process of matrix factorization. MovieLens dataset and Book-Crossing dataset are adopted to evaluate the performance of the proposed algorithm. The results of experiments show that the proposed method can alleviate the impact of tag sparsity and improve the performance of recommender systems.

Efficient fully 3D list-mode TOF PET image reconstruction using a factorized system matrix with an image domain resolution model

International Nuclear Information System (INIS)

Zhou, Jian; Qi, Jinyi

2014-01-01

A factorized system matrix utilizing an image domain resolution model is attractive in fully 3D time-of-flight PET image reconstruction using list-mode data. In this paper, we study a factored model based on sparse matrix factorization that is comprised primarily of a simplified geometrical projection matrix and an image blurring matrix. Beside the commonly-used Siddon’s ray-tracer, we propose another more simplified geometrical projector based on the Bresenham’s ray-tracer which further reduces the computational cost. We discuss in general how to obtain an image blurring matrix associated with a geometrical projector, and provide theoretical analysis that can be used to inspect the efficiency in model factorization. In simulation studies, we investigate the performance of the proposed sparse factorization model in terms of spatial resolution, noise properties and computational cost. The quantitative results reveal that the factorization model can be as efficient as a non-factored model, while its computational cost can be much lower. In addition we conduct Monte Carlo simulations to identify the conditions under which the image resolution model can become more efficient in terms of image contrast recovery. We verify our observations using the provided theoretical analysis. The result offers a general guide to achieve the optimal reconstruction performance based on a sparse factorization model with an image domain resolution model. (paper)

Performance modeling and optimization of sparse matrix-vector multiplication on NVIDIA CUDA platform

NARCIS (Netherlands)

Xu, S.; Xue, W.; Lin, H.X.

2011-01-01

In this article, we discuss the performance modeling and optimization of Sparse Matrix-Vector Multiplication (SpMV) on NVIDIA GPUs using CUDA. SpMV has a very low computation-data ratio and its performance is mainly bound by the memory bandwidth. We propose optimization of SpMV based on ELLPACK from

Nonlocal low-rank and sparse matrix decomposition for spectral CT reconstruction

Science.gov (United States)

Niu, Shanzhou; Yu, Gaohang; Ma, Jianhua; Wang, Jing

2018-02-01

Spectral computed tomography (CT) has been a promising technique in research and clinics because of its ability to produce improved energy resolution images with narrow energy bins. However, the narrow energy bin image is often affected by serious quantum noise because of the limited number of photons used in the corresponding energy bin. To address this problem, we present an iterative reconstruction method for spectral CT using nonlocal low-rank and sparse matrix decomposition (NLSMD), which exploits the self-similarity of patches that are collected in multi-energy images. Specifically, each set of patches can be decomposed into a low-rank component and a sparse component, and the low-rank component represents the stationary background over different energy bins, while the sparse component represents the rest of the different spectral features in individual energy bins. Subsequently, an effective alternating optimization algorithm was developed to minimize the associated objective function. To validate and evaluate the NLSMD method, qualitative and quantitative studies were conducted by using simulated and real spectral CT data. Experimental results show that the NLSMD method improves spectral CT images in terms of noise reduction, artifact suppression and resolution preservation.

Fast wavelet based sparse approximate inverse preconditioner

Energy Technology Data Exchange (ETDEWEB)

Wan, W.L. [Univ. of California, Los Angeles, CA (United States)

1996-12-31

Incomplete LU factorization is a robust preconditioner for both general and PDE problems but unfortunately not easy to parallelize. Recent study of Huckle and Grote and Chow and Saad showed that sparse approximate inverse could be a potential alternative while readily parallelizable. However, for special class of matrix A that comes from elliptic PDE problems, their preconditioners are not optimal in the sense that independent of mesh size. A reason may be that no good sparse approximate inverse exists for the dense inverse matrix. Our observation is that for this kind of matrices, its inverse entries typically have piecewise smooth changes. We can take advantage of this fact and use wavelet compression techniques to construct a better sparse approximate inverse preconditioner. We shall show numerically that our approach is effective for this kind of matrices.

Technique detection software for Sparse Matrices

Directory of Open Access Journals (Sweden)

KHAN Muhammad Taimoor

2009-12-01

Full Text Available Sparse storage formats are techniques for storing and processing the sparse matrix data efficiently. The performance of these storage formats depend upon the distribution of non-zeros, within the matrix in different dimensions. In order to have better results we need a technique that suits best the organization of data in a particular matrix. So the decision of selecting a better technique is the main step towards improving the system's results otherwise the efficiency can be decreased. The purpose of this research is to help identify the best storage format in case of reduced storage size and high processing efficiency for a sparse matrix.

Response of selected binomial coefficients to varying degrees of matrix sparseness and to matrices with known data interrelationships

Science.gov (United States)

Archer, A.W.; Maples, C.G.

1989-01-01

Numerous departures from ideal relationships are revealed by Monte Carlo simulations of widely accepted binomial coefficients. For example, simulations incorporating varying levels of matrix sparseness (presence of zeros indicating lack of data) and computation of expected values reveal that not only are all common coefficients influenced by zero data, but also that some coefficients do not discriminate between sparse or dense matrices (few zero data). Such coefficients computationally merge mutually shared and mutually absent information and do not exploit all the information incorporated within the standard 2 ?? 2 contingency table; therefore, the commonly used formulae for such coefficients are more complicated than the actual range of values produced. Other coefficients do differentiate between mutual presences and absences; however, a number of these coefficients do not demonstrate a linear relationship to matrix sparseness. Finally, simulations using nonrandom matrices with known degrees of row-by-row similarities signify that several coefficients either do not display a reasonable range of values or are nonlinear with respect to known relationships within the data. Analyses with nonrandom matrices yield clues as to the utility of certain coefficients for specific applications. For example, coefficients such as Jaccard, Dice, and Baroni-Urbani and Buser are useful if correction of sparseness is desired, whereas the Russell-Rao coefficient is useful when sparseness correction is not desired. ?? 1989 International Association for Mathematical Geology.

Graph Transformation and Designing Parallel Sparse Matrix Algorithms beyond Data Dependence Analysis

Directory of Open Access Journals (Sweden)

H.X. Lin

2004-01-01

Full Text Available Algorithms are often parallelized based on data dependence analysis manually or by means of parallel compilers. Some vector/matrix computations such as the matrix-vector products with simple data dependence structures (data parallelism can be easily parallelized. For problems with more complicated data dependence structures, parallelization is less straightforward. The data dependence graph is a powerful means for designing and analyzing parallel algorithms. However, for sparse matrix computations, parallelization based on solely exploiting the existing parallelism in an algorithm does not always give satisfactory results. For example, the conventional Gaussian elimination algorithm for the solution of a tri-diagonal system is inherently sequential, so algorithms specially for parallel computation has to be designed. After briefly reviewing different parallelization approaches, a powerful graph formalism for designing parallel algorithms is introduced. This formalism will be discussed using a tri-diagonal system as an example. Its application to general matrix computations is also discussed. Its power in designing parallel algorithms beyond the ability of data dependence analysis is shown by means of a new algorithm called ACER (Alternating Cyclic Elimination and Reduction algorithm.

SIAM 1978 fall meeting and symposium on sparse matrix computations. [Knoxville, Tenn. , October 30--November 3

Energy Technology Data Exchange (ETDEWEB)

1978-01-01

The program and abstracts of the SIAM 1978 fall meeting in Knoxville, Tennessee, are given, along with those of the associated symposium on sparse matrix computations. The papers dealt with both pure mathematics and mathematics applied to many different subject areas. (RWR)

Scalable group level probabilistic sparse factor analysis

DEFF Research Database (Denmark)

Hinrich, Jesper Løve; Nielsen, Søren Føns Vind; Riis, Nicolai Andre Brogaard

2017-01-01

Many data-driven approaches exist to extract neural representations of functional magnetic resonance imaging (fMRI) data, but most of them lack a proper probabilistic formulation. We propose a scalable group level probabilistic sparse factor analysis (psFA) allowing spatially sparse maps, component...... pruning using automatic relevance determination (ARD) and subject specific heteroscedastic spatial noise modeling. For task-based and resting state fMRI, we show that the sparsity constraint gives rise to components similar to those obtained by group independent component analysis. The noise modeling...... shows that noise is reduced in areas typically associated with activation by the experimental design. The psFA model identifies sparse components and the probabilistic setting provides a natural way to handle parameter uncertainties. The variational Bayesian framework easily extends to more complex...

Inference algorithms and learning theory for Bayesian sparse factor analysis

International Nuclear Information System (INIS)

Rattray, Magnus; Sharp, Kevin; Stegle, Oliver; Winn, John

2009-01-01

Bayesian sparse factor analysis has many applications; for example, it has been applied to the problem of inferring a sparse regulatory network from gene expression data. We describe a number of inference algorithms for Bayesian sparse factor analysis using a slab and spike mixture prior. These include well-established Markov chain Monte Carlo (MCMC) and variational Bayes (VB) algorithms as well as a novel hybrid of VB and Expectation Propagation (EP). For the case of a single latent factor we derive a theory for learning performance using the replica method. We compare the MCMC and VB/EP algorithm results with simulated data to the theoretical prediction. The results for MCMC agree closely with the theory as expected. Results for VB/EP are slightly sub-optimal but show that the new algorithm is effective for sparse inference. In large-scale problems MCMC is infeasible due to computational limitations and the VB/EP algorithm then provides a very useful computationally efficient alternative.

Inference algorithms and learning theory for Bayesian sparse factor analysis

Energy Technology Data Exchange (ETDEWEB)

Rattray, Magnus; Sharp, Kevin [School of Computer Science, University of Manchester, Manchester M13 9PL (United Kingdom); Stegle, Oliver [Max-Planck-Institute for Biological Cybernetics, Tuebingen (Germany); Winn, John, E-mail: magnus.rattray@manchester.ac.u [Microsoft Research Cambridge, Roger Needham Building, Cambridge, CB3 0FB (United Kingdom)

2009-12-01

Bayesian sparse factor analysis has many applications; for example, it has been applied to the problem of inferring a sparse regulatory network from gene expression data. We describe a number of inference algorithms for Bayesian sparse factor analysis using a slab and spike mixture prior. These include well-established Markov chain Monte Carlo (MCMC) and variational Bayes (VB) algorithms as well as a novel hybrid of VB and Expectation Propagation (EP). For the case of a single latent factor we derive a theory for learning performance using the replica method. We compare the MCMC and VB/EP algorithm results with simulated data to the theoretical prediction. The results for MCMC agree closely with the theory as expected. Results for VB/EP are slightly sub-optimal but show that the new algorithm is effective for sparse inference. In large-scale problems MCMC is infeasible due to computational limitations and the VB/EP algorithm then provides a very useful computationally efficient alternative.

Permuting sparse rectangular matrices into block-diagonal form

Energy Technology Data Exchange (ETDEWEB)

Aykanat, Cevdet; Pinar, Ali; Catalyurek, Umit V.

2002-12-09

This work investigates the problem of permuting a sparse rectangular matrix into block diagonal form. Block diagonal form of a matrix grants an inherent parallelism for the solution of the deriving problem, as recently investigated in the context of mathematical programming, LU factorization and QR factorization. We propose graph and hypergraph models to represent the nonzero structure of a matrix, which reduce the permutation problem to those of graph partitioning by vertex separator and hypergraph partitioning, respectively. Besides proposing the models to represent sparse matrices and investigating related combinatorial problems, we provide a detailed survey of relevant literature to bridge the gap between different societies, investigate existing techniques for partitioning and propose new ones, and finally present a thorough empirical study of these techniques. Our experiments on a wide range of matrices, using state-of-the-art graph and hypergraph partitioning tools MeTiS and PaT oH, revealed that the proposed methods yield very effective solutions both in terms of solution quality and run time.

Sparse matrix test collections

Energy Technology Data Exchange (ETDEWEB)

Duff, I.

1996-12-31

This workshop will discuss plans for coordinating and developing sets of test matrices for the comparison and testing of sparse linear algebra software. We will talk of plans for the next release (Release 2) of the Harwell-Boeing Collection and recent work on improving the accessibility of this Collection and others through the World Wide Web. There will only be three talks of about 15 to 20 minutes followed by a discussion from the floor.

A sparse matrix based full-configuration interaction algorithm

International Nuclear Information System (INIS)

Rolik, Zoltan; Szabados, Agnes; Surjan, Peter R.

2008-01-01

We present an algorithm related to the full-configuration interaction (FCI) method that makes complete use of the sparse nature of the coefficient vector representing the many-electron wave function in a determinantal basis. Main achievements of the presented sparse FCI (SFCI) algorithm are (i) development of an iteration procedure that avoids the storage of FCI size vectors; (ii) development of an efficient algorithm to evaluate the effect of the Hamiltonian when both the initial and the product vectors are sparse. As a result of point (i) large disk operations can be skipped which otherwise may be a bottleneck of the procedure. At point (ii) we progress by adopting the implementation of the linear transformation by Olsen et al. [J. Chem Phys. 89, 2185 (1988)] for the sparse case, getting the algorithm applicable to larger systems and faster at the same time. The error of a SFCI calculation depends only on the dropout thresholds for the sparse vectors, and can be tuned by controlling the amount of system memory passed to the procedure. The algorithm permits to perform FCI calculations on single node workstations for systems previously accessible only by supercomputers

Uncovering Transcriptional Regulatory Networks by Sparse Bayesian Factor Model

Directory of Open Access Journals (Sweden)

Qi Yuan(Alan

2010-01-01

Full Text Available Abstract The problem of uncovering transcriptional regulation by transcription factors (TFs based on microarray data is considered. A novel Bayesian sparse correlated rectified factor model (BSCRFM is proposed that models the unknown TF protein level activity, the correlated regulations between TFs, and the sparse nature of TF-regulated genes. The model admits prior knowledge from existing database regarding TF-regulated target genes based on a sparse prior and through a developed Gibbs sampling algorithm, a context-specific transcriptional regulatory network specific to the experimental condition of the microarray data can be obtained. The proposed model and the Gibbs sampling algorithm were evaluated on the simulated systems, and results demonstrated the validity and effectiveness of the proposed approach. The proposed model was then applied to the breast cancer microarray data of patients with Estrogen Receptor positive ( status and Estrogen Receptor negative ( status, respectively.

Sparse Non-negative Matrix Factor 2-D Deconvolution for Automatic Transcription of Polyphonic Music

DEFF Research Database (Denmark)

Schmidt, Mikkel N.; Mørup, Morten

2006-01-01

We present a novel method for automatic transcription of polyphonic music based on a recently published algorithm for non-negative matrix factor 2-D deconvolution. The method works by simultaneously estimating a time-frequency model for an instrument and a pattern corresponding to the notes which...... are played based on a log-frequency spectrogram of the music....

A Nonnegative Latent Factor Model for Large-Scale Sparse Matrices in Recommender Systems via Alternating Direction Method.

Science.gov (United States)

Luo, Xin; Zhou, MengChu; Li, Shuai; You, Zhuhong; Xia, Yunni; Zhu, Qingsheng

2016-03-01

Nonnegative matrix factorization (NMF)-based models possess fine representativeness of a target matrix, which is critically important in collaborative filtering (CF)-based recommender systems. However, current NMF-based CF recommenders suffer from the problem of high computational and storage complexity, as well as slow convergence rate, which prevents them from industrial usage in context of big data. To address these issues, this paper proposes an alternating direction method (ADM)-based nonnegative latent factor (ANLF) model. The main idea is to implement the ADM-based optimization with regard to each single feature, to obtain high convergence rate as well as low complexity. Both computational and storage costs of ANLF are linear with the size of given data in the target matrix, which ensures high efficiency when dealing with extremely sparse matrices usually seen in CF problems. As demonstrated by the experiments on large, real data sets, ANLF also ensures fast convergence and high prediction accuracy, as well as the maintenance of nonnegativity constraints. Moreover, it is simple and easy to implement for real applications of learning systems.

Linear-scaling density-functional simulations of charged point defects in Al2O3 using hierarchical sparse matrix algebra.

Science.gov (United States)

Hine, N D M; Haynes, P D; Mostofi, A A; Payne, M C

2010-09-21

We present calculations of formation energies of defects in an ionic solid (Al(2)O(3)) extrapolated to the dilute limit, corresponding to a simulation cell of infinite size. The large-scale calculations required for this extrapolation are enabled by developments in the approach to parallel sparse matrix algebra operations, which are central to linear-scaling density-functional theory calculations. The computational cost of manipulating sparse matrices, whose sizes are determined by the large number of basis functions present, is greatly improved with this new approach. We present details of the sparse algebra scheme implemented in the ONETEP code using hierarchical sparsity patterns, and demonstrate its use in calculations on a wide range of systems, involving thousands of atoms on hundreds to thousands of parallel processes.

Sparse PCA with Oracle Property.

Science.gov (United States)

Gu, Quanquan; Wang, Zhaoran; Liu, Han

In this paper, we study the estimation of the k -dimensional sparse principal subspace of covariance matrix Σ in the high-dimensional setting. We aim to recover the oracle principal subspace solution, i.e., the principal subspace estimator obtained assuming the true support is known a priori. To this end, we propose a family of estimators based on the semidefinite relaxation of sparse PCA with novel regularizations. In particular, under a weak assumption on the magnitude of the population projection matrix, one estimator within this family exactly recovers the true support with high probability, has exact rank- k , and attains a [Formula: see text] statistical rate of convergence with s being the subspace sparsity level and n the sample size. Compared to existing support recovery results for sparse PCA, our approach does not hinge on the spiked covariance model or the limited correlation condition. As a complement to the first estimator that enjoys the oracle property, we prove that, another estimator within the family achieves a sharper statistical rate of convergence than the standard semidefinite relaxation of sparse PCA, even when the previous assumption on the magnitude of the projection matrix is violated. We validate the theoretical results by numerical experiments on synthetic datasets.

A fast algorithm for sparse matrix computations related to inversion

International Nuclear Information System (INIS)

Li, S.; Wu, W.; Darve, E.

2013-01-01

We have developed a fast algorithm for computing certain entries of the inverse of a sparse matrix. Such computations are critical to many applications, such as the calculation of non-equilibrium Green’s functions G r and G for nano-devices. The FIND (Fast Inverse using Nested Dissection) algorithm is optimal in the big-O sense. However, in practice, FIND suffers from two problems due to the width-2 separators used by its partitioning scheme. One problem is the presence of a large constant factor in the computational cost of FIND. The other problem is that the partitioning scheme used by FIND is incompatible with most existing partitioning methods and libraries for nested dissection, which all use width-1 separators. Our new algorithm resolves these problems by thoroughly decomposing the computation process such that width-1 separators can be used, resulting in a significant speedup over FIND for realistic devices — up to twelve-fold in simulation. The new algorithm also has the added advantage that desired off-diagonal entries can be computed for free. Consequently, our algorithm is faster than the current state-of-the-art recursive methods for meshes of any size. Furthermore, the framework used in the analysis of our algorithm is the first attempt to explicitly apply the widely-used relationship between mesh nodes and matrix computations to the problem of multiple eliminations with reuse of intermediate results. This framework makes our algorithm easier to generalize, and also easier to compare against other methods related to elimination trees. Finally, our accuracy analysis shows that the algorithms that require back-substitution are subject to significant extra round-off errors, which become extremely large even for some well-conditioned matrices or matrices with only moderately large condition numbers. When compared to these back-substitution algorithms, our algorithm is generally a few orders of magnitude more accurate, and our produced round-off errors

A fast algorithm for sparse matrix computations related to inversion

Energy Technology Data Exchange (ETDEWEB)

Li, S., E-mail: lisong@stanford.edu [Institute for Computational and Mathematical Engineering, Stanford University, 496 Lomita Mall, Durand Building, Stanford, CA 94305 (United States); Wu, W. [Department of Electrical Engineering, Stanford University, 350 Serra Mall, Packard Building, Room 268, Stanford, CA 94305 (United States); Darve, E. [Institute for Computational and Mathematical Engineering, Stanford University, 496 Lomita Mall, Durand Building, Stanford, CA 94305 (United States); Department of Mechanical Engineering, Stanford University, 496 Lomita Mall, Durand Building, Room 209, Stanford, CA 94305 (United States)

2013-06-01

We have developed a fast algorithm for computing certain entries of the inverse of a sparse matrix. Such computations are critical to many applications, such as the calculation of non-equilibrium Green’s functions G{sup r} and G{sup <} for nano-devices. The FIND (Fast Inverse using Nested Dissection) algorithm is optimal in the big-O sense. However, in practice, FIND suffers from two problems due to the width-2 separators used by its partitioning scheme. One problem is the presence of a large constant factor in the computational cost of FIND. The other problem is that the partitioning scheme used by FIND is incompatible with most existing partitioning methods and libraries for nested dissection, which all use width-1 separators. Our new algorithm resolves these problems by thoroughly decomposing the computation process such that width-1 separators can be used, resulting in a significant speedup over FIND for realistic devices — up to twelve-fold in simulation. The new algorithm also has the added advantage that desired off-diagonal entries can be computed for free. Consequently, our algorithm is faster than the current state-of-the-art recursive methods for meshes of any size. Furthermore, the framework used in the analysis of our algorithm is the first attempt to explicitly apply the widely-used relationship between mesh nodes and matrix computations to the problem of multiple eliminations with reuse of intermediate results. This framework makes our algorithm easier to generalize, and also easier to compare against other methods related to elimination trees. Finally, our accuracy analysis shows that the algorithms that require back-substitution are subject to significant extra round-off errors, which become extremely large even for some well-conditioned matrices or matrices with only moderately large condition numbers. When compared to these back-substitution algorithms, our algorithm is generally a few orders of magnitude more accurate, and our produced round

ImWalkMF: Joint matrix factorization and implicit walk integrative learning for recommendation

KAUST Repository

Zhang, Chuxu

2018-01-15

Data sparsity and cold-start problems are prevalent in recommender systems. To address such problems, both the observable explicit social information (e.g., user-user trust connections) and the inferable implicit correlations (e.g., implicit neighbors computed by similarity measurement) have been introduced to complement user-item ratings data for improving the performances of traditional model-based recommendation algorithms such as matrix factorization. Although effective, (1) the utilization of the explicit user-user social relationships suffers from the weakness of unavailability in real systems such as Netflix or the issue of sparse observable content like 0.03% trust density in Epinions, thus there is no or little explicit social information that can be employed to improve baseline model in real applications; (2) the current similarity measurement approaches focus on inferring implicit correlations between a user (item) and their direct neighbors or top-k similar neighbors based on user-item ratings bipartite network, so that they fail to comprehensively unfold the indirect potential relationships among users and items. To solve these issues regarding both explicit/implicit social recommendation algorithms, we design a joint model of matrix factorization and implicit walk integrative learning, i.e., ImWalkMF, which only uses explicit ratings information yet models both direct rating feedbacks and multiple direct/indirect implicit correlations among users and items from a random walk perspective. We further propose a combined strategy for training two independent components in the proposed model based on sampling. The experimental results on two real-world sparse datasets demonstrate that ImWalkMF outperforms the traditional regularized/probabilistic matrix factorization models as well as other competitive baselines that utilize explicit/implicit social information.

Decoding the encoding of functional brain networks: An fMRI classification comparison of non-negative matrix factorization (NMF), independent component analysis (ICA), and sparse coding algorithms.

Science.gov (United States)

Xie, Jianwen; Douglas, Pamela K; Wu, Ying Nian; Brody, Arthur L; Anderson, Ariana E

2017-04-15

Brain networks in fMRI are typically identified using spatial independent component analysis (ICA), yet other mathematical constraints provide alternate biologically-plausible frameworks for generating brain networks. Non-negative matrix factorization (NMF) would suppress negative BOLD signal by enforcing positivity. Spatial sparse coding algorithms (L1 Regularized Learning and K-SVD) would impose local specialization and a discouragement of multitasking, where the total observed activity in a single voxel originates from a restricted number of possible brain networks. The assumptions of independence, positivity, and sparsity to encode task-related brain networks are compared; the resulting brain networks within scan for different constraints are used as basis functions to encode observed functional activity. These encodings are then decoded using machine learning, by using the time series weights to predict within scan whether a subject is viewing a video, listening to an audio cue, or at rest, in 304 fMRI scans from 51 subjects. The sparse coding algorithm of L1 Regularized Learning outperformed 4 variations of ICA (pcoding algorithms. Holding constant the effect of the extraction algorithm, encodings using sparser spatial networks (containing more zero-valued voxels) had higher classification accuracy (pcoding algorithms suggests that algorithms which enforce sparsity, discourage multitasking, and promote local specialization may capture better the underlying source processes than those which allow inexhaustible local processes such as ICA. Negative BOLD signal may capture task-related activations. Copyright © 2017 Elsevier B.V. All rights reserved.

Computing the sparse matrix vector product using block-based kernels without zero padding on processors with AVX-512 instructions

Directory of Open Access Journals (Sweden)

Bérenger Bramas

2018-04-01

Full Text Available The sparse matrix-vector product (SpMV is a fundamental operation in many scientific applications from various fields. The High Performance Computing (HPC community has therefore continuously invested a lot of effort to provide an efficient SpMV kernel on modern CPU architectures. Although it has been shown that block-based kernels help to achieve high performance, they are difficult to use in practice because of the zero padding they require. In the current paper, we propose new kernels using the AVX-512 instruction set, which makes it possible to use a blocking scheme without any zero padding in the matrix memory storage. We describe mask-based sparse matrix formats and their corresponding SpMV kernels highly optimized in assembly language. Considering that the optimal blocking size depends on the matrix, we also provide a method to predict the best kernel to be used utilizing a simple interpolation of results from previous executions. We compare the performance of our approach to that of the Intel MKL CSR kernel and the CSR5 open-source package on a set of standard benchmark matrices. We show that we can achieve significant improvements in many cases, both for sequential and for parallel executions. Finally, we provide the corresponding code in an open source library, called SPC5.

Optimization of sparse matrix-vector multiplication on emerging multicore platforms

Energy Technology Data Exchange (ETDEWEB)

Williams, Samuel [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States); Oliker, Leonid [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Vuduc, Richard [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Shalf, John [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Yelick, Katherine [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States); Demmel, James [Univ. of California, Berkeley, CA (United States)

2007-01-01

We are witnessing a dramatic change in computer architecture due to the multicore paradigm shift, as every electronic device from cell phones to supercomputers confronts parallelism of unprecedented scale. To fully unleash the potential of these systems, the HPC community must develop multicore specific optimization methodologies for important scientific computations. In this work, we examine sparse matrix-vector multiply (SpMV) - one of the most heavily used kernels in scientific computing - across a broad spectrum of multicore designs. Our experimental platform includes the homogeneous AMD dual-core and Intel quad-core designs, the heterogeneous STI Cell, as well as the first scientific study of the highly multithreaded Sun Niagara2. We present several optimization strategies especially effective for the multicore environment, and demonstrate significant performance improvements compared to existing state-of-the-art serial and parallel SpMV implementations. Additionally, we present key insights into the architectural tradeoffs of leading multicore design strategies, in the context of demanding memory-bound numerical algorithms.

Link Prediction via Convex Nonnegative Matrix Factorization on Multiscale Blocks

Directory of Open Access Journals (Sweden)

Enming Dong

2014-01-01

Full Text Available Low rank matrices approximations have been used in link prediction for networks, which are usually global optimal methods and lack of using the local information. The block structure is a significant local feature of matrices: entities in the same block have similar values, which implies that links are more likely to be found within dense blocks. We use this insight to give a probabilistic latent variable model for finding missing links by convex nonnegative matrix factorization with block detection. The experiments show that this method gives better prediction accuracy than original method alone. Different from the original low rank matrices approximations methods for link prediction, the sparseness of solutions is in accord with the sparse property for most real complex networks. Scaling to massive size network, we use the block information mapping matrices onto distributed architectures and give a divide-and-conquer prediction method. The experiments show that it gives better results than common neighbors method when the networks have a large number of missing links.

High-SNR spectrum measurement based on Hadamard encoding and sparse reconstruction

Science.gov (United States)

Wang, Zhaoxin; Yue, Jiang; Han, Jing; Li, Long; Jin, Yong; Gao, Yuan; Li, Baoming

2017-12-01

The denoising capabilities of the H-matrix and cyclic S-matrix based on the sparse reconstruction, employed in the Pixel of Focal Plane Coded Visible Spectrometer for spectrum measurement are investigated, where the spectrum is sparse in a known basis. In the measurement process, the digital micromirror device plays an important role, which implements the Hadamard coding. In contrast with Hadamard transform spectrometry, based on the shift invariability, this spectrometer may have the advantage of a high efficiency. Simulations and experiments show that the nonlinear solution with a sparse reconstruction has a better signal-to-noise ratio than the linear solution and the H-matrix outperforms the cyclic S-matrix whether the reconstruction method is nonlinear or linear.

Optimization of Sparse Matrix-Vector Multiplication on Emerging Multicore Platforms

Energy Technology Data Exchange (ETDEWEB)

Williams, Samuel; Oliker, Leonid; Vuduc, Richard; Shalf, John; Yelick, Katherine; Demmel, James

2008-10-16

We are witnessing a dramatic change in computer architecture due to the multicore paradigm shift, as every electronic device from cell phones to supercomputers confronts parallelism of unprecedented scale. To fully unleash the potential of these systems, the HPC community must develop multicore specific-optimization methodologies for important scientific computations. In this work, we examine sparse matrix-vector multiply (SpMV) - one of the most heavily used kernels in scientific computing - across a broad spectrum of multicore designs. Our experimental platform includes the homogeneous AMD quad-core, AMD dual-core, and Intel quad-core designs, the heterogeneous STI Cell, as well as one of the first scientific studies of the highly multithreaded Sun Victoria Falls (a Niagara2 SMP). We present several optimization strategies especially effective for the multicore environment, and demonstrate significant performance improvements compared to existing state-of-the-art serial and parallel SpMV implementations. Additionally, we present key insights into the architectural trade-offs of leading multicore design strategies, in the context of demanding memory-bound numerical algorithms.

Color normalization of histology slides using graph regularized sparse NMF

Science.gov (United States)

Sha, Lingdao; Schonfeld, Dan; Sethi, Amit

2017-03-01

Computer based automatic medical image processing and quantification are becoming popular in digital pathology. However, preparation of histology slides can vary widely due to differences in staining equipment, procedures and reagents, which can reduce the accuracy of algorithms that analyze their color and texture information. To re- duce the unwanted color variations, various supervised and unsupervised color normalization methods have been proposed. Compared with supervised color normalization methods, unsupervised color normalization methods have advantages of time and cost efficient and universal applicability. Most of the unsupervised color normaliza- tion methods for histology are based on stain separation. Based on the fact that stain concentration cannot be negative and different parts of the tissue absorb different stains, nonnegative matrix factorization (NMF), and particular its sparse version (SNMF), are good candidates for stain separation. However, most of the existing unsupervised color normalization method like PCA, ICA, NMF and SNMF fail to consider important information about sparse manifolds that its pixels occupy, which could potentially result in loss of texture information during color normalization. Manifold learning methods like Graph Laplacian have proven to be very effective in interpreting high-dimensional data. In this paper, we propose a novel unsupervised stain separation method called graph regularized sparse nonnegative matrix factorization (GSNMF). By considering the sparse prior of stain concentration together with manifold information from high-dimensional image data, our method shows better performance in stain color deconvolution than existing unsupervised color deconvolution methods, especially in keeping connected texture information. To utilized the texture information, we construct a nearest neighbor graph between pixels within a spatial area of an image based on their distances using heat kernal in lαβ space. The

The Real-Valued Sparse Direction of Arrival (DOA Estimation Based on the Khatri-Rao Product

Directory of Open Access Journals (Sweden)

Tao Chen

2016-05-01

Full Text Available There is a problem that complex operation which leads to a heavy calculation burden is required when the direction of arrival (DOA of a sparse signal is estimated by using the array covariance matrix. The solution of the multiple measurement vectors (MMV model is difficult. In this paper, a real-valued sparse DOA estimation algorithm based on the Khatri-Rao (KR product called the L1-RVSKR is proposed. The proposed algorithm is based on the sparse representation of the array covariance matrix. The array covariance matrix is transformed to a real-valued matrix via a unitary transformation so that a real-valued sparse model is achieved. The real-valued sparse model is vectorized for transforming to a single measurement vector (SMV model, and a new virtual overcomplete dictionary is constructed according to the KR product’s property. Finally, the sparse DOA estimation is solved by utilizing the idea of a sparse representation of array covariance vectors (SRACV. The simulation results demonstrate the superior performance and the low computational complexity of the proposed algorithm.

Parallelism in matrix computations

CERN Document Server

Gallopoulos, Efstratios; Sameh, Ahmed H

2016-01-01

This book is primarily intended as a research monograph that could also be used in graduate courses for the design of parallel algorithms in matrix computations. It assumes general but not extensive knowledge of numerical linear algebra, parallel architectures, and parallel programming paradigms. The book consists of four parts: (I) Basics; (II) Dense and Special Matrix Computations; (III) Sparse Matrix Computations; and (IV) Matrix functions and characteristics. Part I deals with parallel programming paradigms and fundamental kernels, including reordering schemes for sparse matrices. Part II is devoted to dense matrix computations such as parallel algorithms for solving linear systems, linear least squares, the symmetric algebraic eigenvalue problem, and the singular-value decomposition. It also deals with the development of parallel algorithms for special linear systems such as banded ,Vandermonde ,Toeplitz ,and block Toeplitz systems. Part III addresses sparse matrix computations: (a) the development of pa...

Efficient Computation of Sparse Matrix Functions for Large-Scale Electronic Structure Calculations: The CheSS Library.

Science.gov (United States)

Mohr, Stephan; Dawson, William; Wagner, Michael; Caliste, Damien; Nakajima, Takahito; Genovese, Luigi

2017-10-10

We present CheSS, the "Chebyshev Sparse Solvers" library, which has been designed to solve typical problems arising in large-scale electronic structure calculations using localized basis sets. The library is based on a flexible and efficient expansion in terms of Chebyshev polynomials and presently features the calculation of the density matrix, the calculation of matrix powers for arbitrary powers, and the extraction of eigenvalues in a selected interval. CheSS is able to exploit the sparsity of the matrices and scales linearly with respect to the number of nonzero entries, making it well-suited for large-scale calculations. The approach is particularly adapted for setups leading to small spectral widths of the involved matrices and outperforms alternative methods in this regime. By coupling CheSS to the DFT code BigDFT, we show that such a favorable setup is indeed possible in practice. In addition, the approach based on Chebyshev polynomials can be massively parallelized, and CheSS exhibits excellent scaling up to thousands of cores even for relatively small matrix sizes.

A Fast Gradient Method for Nonnegative Sparse Regression With Self-Dictionary

Science.gov (United States)

Gillis, Nicolas; Luce, Robert

2018-01-01

A nonnegative matrix factorization (NMF) can be computed efficiently under the separability assumption, which asserts that all the columns of the given input data matrix belong to the cone generated by a (small) subset of them. The provably most robust methods to identify these conic basis columns are based on nonnegative sparse regression and self dictionaries, and require the solution of large-scale convex optimization problems. In this paper we study a particular nonnegative sparse regression model with self dictionary. As opposed to previously proposed models, this model yields a smooth optimization problem where the sparsity is enforced through linear constraints. We show that the Euclidean projection on the polyhedron defined by these constraints can be computed efficiently, and propose a fast gradient method to solve our model. We compare our algorithm with several state-of-the-art methods on synthetic data sets and real-world hyperspectral images.

Dictionary Learning Based on Nonnegative Matrix Factorization Using Parallel Coordinate Descent

Directory of Open Access Journals (Sweden)

Zunyi Tang

2013-01-01

Full Text Available Sparse representation of signals via an overcomplete dictionary has recently received much attention as it has produced promising results in various applications. Since the nonnegativities of the signals and the dictionary are required in some applications, for example, multispectral data analysis, the conventional dictionary learning methods imposed simply with nonnegativity may become inapplicable. In this paper, we propose a novel method for learning a nonnegative, overcomplete dictionary for such a case. This is accomplished by posing the sparse representation of nonnegative signals as a problem of nonnegative matrix factorization (NMF with a sparsity constraint. By employing the coordinate descent strategy for optimization and extending it to multivariable case for processing in parallel, we develop a so-called parallel coordinate descent dictionary learning (PCDDL algorithm, which is structured by iteratively solving the two optimal problems, the learning process of the dictionary and the estimating process of the coefficients for constructing the signals. Numerical experiments demonstrate that the proposed algorithm performs better than the conventional nonnegative K-SVD (NN-KSVD algorithm and several other algorithms for comparison. What is more, its computational consumption is remarkably lower than that of the compared algorithms.

Removing flicker based on sparse color correspondences in old film restoration

Science.gov (United States)

Huang, Xi; Ding, Youdong; Yu, Bing; Xia, Tianran

2018-04-01

In the long history of human civilization, archived film is an indispensable part of it, and using digital method to repair damaged film is also a mainstream trend nowadays. In this paper, we propose a sparse color correspondences based technique to remove fading flicker for old films. Our model, combined with multi frame images to establish a simple correction model, includes three key steps. Firstly, we recover sparse color correspondences in the input frames to build a matrix with many missing entries. Secondly, we present a low-rank matrix factorization approach to estimate the unknown parameters of this model. Finally, we adopt a two-step strategy that divide the estimated parameters into reference frame parameters for color recovery correction and other frame parameters for color consistency correction to remove flicker. Our method combined multi-frames takes continuity of the input sequence into account, and the experimental results show the method can remove fading flicker efficiently.

Sparse coding reveals greater functional connectivity in female brains during naturalistic emotional experience.

Directory of Open Access Journals (Sweden)

Yudan Ren

Full Text Available Functional neuroimaging is widely used to examine changes in brain function associated with age, gender or neuropsychiatric conditions. FMRI (functional magnetic resonance imaging studies employ either laboratory-designed tasks that engage the brain with abstracted and repeated stimuli, or resting state paradigms with little behavioral constraint. Recently, novel neuroimaging paradigms using naturalistic stimuli are gaining increasing attraction, as they offer an ecologically-valid condition to approximate brain function in real life. Wider application of naturalistic paradigms in exploring individual differences in brain function, however, awaits further advances in statistical methods for modeling dynamic and complex dataset. Here, we developed a novel data-driven strategy that employs group sparse representation to assess gender differences in brain responses during naturalistic emotional experience. Comparing to independent component analysis (ICA, sparse coding algorithm considers the intrinsic sparsity of neural coding and thus could be more suitable in modeling dynamic whole-brain fMRI signals. An online dictionary learning and sparse coding algorithm was applied to the aggregated fMRI signals from both groups, which was subsequently factorized into a common time series signal dictionary matrix and the associated weight coefficient matrix. Our results demonstrate that group sparse representation can effectively identify gender differences in functional brain network during natural viewing, with improved sensitivity and reliability over ICA-based method. Group sparse representation hence offers a superior data-driven strategy for examining brain function during naturalistic conditions, with great potential for clinical application in neuropsychiatric disorders.

A Spectral Algorithm for Envelope Reduction of Sparse Matrices

Science.gov (United States)

Barnard, Stephen T.; Pothen, Alex; Simon, Horst D.

1993-01-01

The problem of reordering a sparse symmetric matrix to reduce its envelope size is considered. A new spectral algorithm for computing an envelope-reducing reordering is obtained by associating a Laplacian matrix with the given matrix and then sorting the components of a specified eigenvector of the Laplacian. This Laplacian eigenvector solves a continuous relaxation of a discrete problem related to envelope minimization called the minimum 2-sum problem. The permutation vector computed by the spectral algorithm is a closest permutation vector to the specified Laplacian eigenvector. Numerical results show that the new reordering algorithm usually computes smaller envelope sizes than those obtained from the current standard algorithms such as Gibbs-Poole-Stockmeyer (GPS) or SPARSPAK reverse Cuthill-McKee (RCM), in some cases reducing the envelope by more than a factor of two.

Codesign of Beam Pattern and Sparse Frequency Waveforms for MIMO Radar

Directory of Open Access Journals (Sweden)

Chaoyun Mai

2015-01-01

Full Text Available Multiple-input multiple-output (MIMO radar takes the advantages of high degrees of freedom for beam pattern design and waveform optimization, because each antenna in centralized MIMO radar system can transmit different signal waveforms. When continuous band is divided into several pieces, sparse frequency radar waveforms play an important role due to the special pattern of the sparse spectrum. In this paper, we start from the covariance matrix of the transmitted waveform and extend the concept of sparse frequency design to the study of MIMO radar beam pattern. With this idea in mind, we first solve the problem of semidefinite constraint by optimization tools and get the desired covariance matrix of the ideal beam pattern. Then, we use the acquired covariance matrix and generalize the objective function by adding the constraint of both constant modulus of the signals and corresponding spectrum. Finally, we solve the objective function by the cyclic algorithm and obtain the sparse frequency MIMO radar waveforms with desired beam pattern. The simulation results verify the effectiveness of this method.

Parallel transposition of sparse data structures

DEFF Research Database (Denmark)

Wang, Hao; Liu, Weifeng; Hou, Kaixi

2016-01-01

Many applications in computational sciences and social sciences exploit sparsity and connectivity of acquired data. Even though many parallel sparse primitives such as sparse matrix-vector (SpMV) multiplication have been extensively studied, some other important building blocks, e.g., parallel tr...... transposition in the latest vendor-supplied library on an Intel multicore CPU platform, and the MergeTrans approach achieves on average of 3.4-fold (up to 11.7-fold) speedup on an Intel Xeon Phi many-core processor....

Matrix completion by deep matrix factorization.

Science.gov (United States)

Fan, Jicong; Cheng, Jieyu

2018-02-01

Conventional methods of matrix completion are linear methods that are not effective in handling data of nonlinear structures. Recently a few researchers attempted to incorporate nonlinear techniques into matrix completion but there still exists considerable limitations. In this paper, a novel method called deep matrix factorization (DMF) is proposed for nonlinear matrix completion. Different from conventional matrix completion methods that are based on linear latent variable models, DMF is on the basis of a nonlinear latent variable model. DMF is formulated as a deep-structure neural network, in which the inputs are the low-dimensional unknown latent variables and the outputs are the partially observed variables. In DMF, the inputs and the parameters of the multilayer neural network are simultaneously optimized to minimize the reconstruction errors for the observed entries. Then the missing entries can be readily recovered by propagating the latent variables to the output layer. DMF is compared with state-of-the-art methods of linear and nonlinear matrix completion in the tasks of toy matrix completion, image inpainting and collaborative filtering. The experimental results verify that DMF is able to provide higher matrix completion accuracy than existing methods do and DMF is applicable to large matrices. Copyright © 2017 Elsevier Ltd. All rights reserved.

Parallel sparse direct solver for integrated circuit simulation

CERN Document Server

Chen, Xiaoming; Yang, Huazhong

2017-01-01

This book describes algorithmic methods and parallelization techniques to design a parallel sparse direct solver which is specifically targeted at integrated circuit simulation problems. The authors describe a complete flow and detailed parallel algorithms of the sparse direct solver. They also show how to improve the performance by simple but effective numerical techniques. The sparse direct solver techniques described can be applied to any SPICE-like integrated circuit simulator and have been proven to be high-performance in actual circuit simulation. Readers will benefit from the state-of-the-art parallel integrated circuit simulation techniques described in this book, especially the latest parallel sparse matrix solution techniques. · Introduces complicated algorithms of sparse linear solvers, using concise principles and simple examples, without complex theory or lengthy derivations; · Describes a parallel sparse direct solver that can be adopted to accelerate any SPICE-like integrated circuit simulato...

Structure-based bayesian sparse reconstruction

KAUST Repository

Quadeer, Ahmed Abdul

2012-12-01

Sparse signal reconstruction algorithms have attracted research attention due to their wide applications in various fields. In this paper, we present a simple Bayesian approach that utilizes the sparsity constraint and a priori statistical information (Gaussian or otherwise) to obtain near optimal estimates. In addition, we make use of the rich structure of the sensing matrix encountered in many signal processing applications to develop a fast sparse recovery algorithm. The computational complexity of the proposed algorithm is very low compared with the widely used convex relaxation methods as well as greedy matching pursuit techniques, especially at high sparsity. © 1991-2012 IEEE.

A FPC-ROOT Algorithm for 2D-DOA Estimation in Sparse Array

Directory of Open Access Journals (Sweden)

Wenhao Zeng

2016-01-01

Full Text Available To improve the performance of two-dimensional direction-of-arrival (2D DOA estimation in sparse array, this paper presents a Fixed Point Continuation Polynomial Roots (FPC-ROOT algorithm. Firstly, a signal model for DOA estimation is established based on matrix completion and it can be proved that the proposed model meets Null Space Property (NSP. Secondly, left and right singular vectors of received signals matrix are achieved using the matrix completion algorithm. Finally, 2D DOA estimation can be acquired through solving the polynomial roots. The proposed algorithm can achieve high accuracy of 2D DOA estimation in sparse array, without solving autocorrelation matrix of received signals and scanning of two-dimensional spectral peak. Besides, it decreases the number of antennas and lowers computational complexity and meanwhile avoids the angle ambiguity problem. Computer simulations demonstrate that the proposed FPC-ROOT algorithm can obtain the 2D DOA estimation precisely in sparse array.

Biclustering via Sparse Singular Value Decomposition

KAUST Repository

Lee, Mihee

2010-02-16

Sparse singular value decomposition (SSVD) is proposed as a new exploratory analysis tool for biclustering or identifying interpretable row-column associations within high-dimensional data matrices. SSVD seeks a low-rank, checkerboard structured matrix approximation to data matrices. The desired checkerboard structure is achieved by forcing both the left- and right-singular vectors to be sparse, that is, having many zero entries. By interpreting singular vectors as regression coefficient vectors for certain linear regressions, sparsity-inducing regularization penalties are imposed to the least squares regression to produce sparse singular vectors. An efficient iterative algorithm is proposed for computing the sparse singular vectors, along with some discussion of penalty parameter selection. A lung cancer microarray dataset and a food nutrition dataset are used to illustrate SSVD as a biclustering method. SSVD is also compared with some existing biclustering methods using simulated datasets. © 2010, The International Biometric Society.

Predicting protein-protein interactions from multimodal biological data sources via nonnegative matrix tri-factorization.

Science.gov (United States)

Wang, Hua; Huang, Heng; Ding, Chris; Nie, Feiping

2013-04-01

Protein interactions are central to all the biological processes and structural scaffolds in living organisms, because they orchestrate a number of cellular processes such as metabolic pathways and immunological recognition. Several high-throughput methods, for example, yeast two-hybrid system and mass spectrometry method, can help determine protein interactions, which, however, suffer from high false-positive rates. Moreover, many protein interactions predicted by one method are not supported by another. Therefore, computational methods are necessary and crucial to complete the interactome expeditiously. In this work, we formulate the problem of predicting protein interactions from a new mathematical perspective--sparse matrix completion, and propose a novel nonnegative matrix factorization (NMF)-based matrix completion approach to predict new protein interactions from existing protein interaction networks. Through using manifold regularization, we further develop our method to integrate different biological data sources, such as protein sequences, gene expressions, protein structure information, etc. Extensive experimental results on four species, Saccharomyces cerevisiae, Drosophila melanogaster, Homo sapiens, and Caenorhabditis elegans, have shown that our new methods outperform related state-of-the-art protein interaction prediction methods.

Non-negative Matrix Factorization for Binary Data

DEFF Research Database (Denmark)

Larsen, Jacob Søgaard; Clemmensen, Line Katrine Harder

We propose the Logistic Non-negative Matrix Factorization for decomposition of binary data. Binary data are frequently generated in e.g. text analysis, sensory data, market basket data etc. A common method for analysing non-negative data is the Non-negative Matrix Factorization, though...... this is in theory not appropriate for binary data, and thus we propose a novel Non-negative Matrix Factorization based on the logistic link function. Furthermore we generalize the method to handle missing data. The formulation of the method is compared to a previously proposed method (Tome et al., 2015). We compare...... the performance of the Logistic Non-negative Matrix Factorization to Least Squares Non-negative Matrix Factorization and Kullback-Leibler (KL) Non-negative Matrix Factorization on sets of binary data: a synthetic dataset, a set of student comments on their professors collected in a binary term-document matrix...

Robust and sparse correlation matrix estimation for the analysis of high-dimensional genomics data.

Science.gov (United States)

Serra, Angela; Coretto, Pietro; Fratello, Michele; Tagliaferri, Roberto; Stegle, Oliver

2018-02-15

Microarray technology can be used to study the expression of thousands of genes across a number of different experimental conditions, usually hundreds. The underlying principle is that genes sharing similar expression patterns, across different samples, can be part of the same co-expression system, or they may share the same biological functions. Groups of genes are usually identified based on cluster analysis. Clustering methods rely on the similarity matrix between genes. A common choice to measure similarity is to compute the sample correlation matrix. Dimensionality reduction is another popular data analysis task which is also based on covariance/correlation matrix estimates. Unfortunately, covariance/correlation matrix estimation suffers from the intrinsic noise present in high-dimensional data. Sources of noise are: sampling variations, presents of outlying sample units, and the fact that in most cases the number of units is much larger than the number of genes. In this paper, we propose a robust correlation matrix estimator that is regularized based on adaptive thresholding. The resulting method jointly tames the effects of the high-dimensionality, and data contamination. Computations are easy to implement and do not require hand tunings. Both simulated and real data are analyzed. A Monte Carlo experiment shows that the proposed method is capable of remarkable performances. Our correlation metric is more robust to outliers compared with the existing alternatives in two gene expression datasets. It is also shown how the regularization allows to automatically detect and filter spurious correlations. The same regularization is also extended to other less robust correlation measures. Finally, we apply the ARACNE algorithm on the SyNTreN gene expression data. Sensitivity and specificity of the reconstructed network is compared with the gold standard. We show that ARACNE performs better when it takes the proposed correlation matrix estimator as input. The R

Convex Banding of the Covariance Matrix.

Science.gov (United States)

Bien, Jacob; Bunea, Florentina; Xiao, Luo

2016-01-01

We introduce a new sparse estimator of the covariance matrix for high-dimensional models in which the variables have a known ordering. Our estimator, which is the solution to a convex optimization problem, is equivalently expressed as an estimator which tapers the sample covariance matrix by a Toeplitz, sparsely-banded, data-adaptive matrix. As a result of this adaptivity, the convex banding estimator enjoys theoretical optimality properties not attained by previous banding or tapered estimators. In particular, our convex banding estimator is minimax rate adaptive in Frobenius and operator norms, up to log factors, over commonly-studied classes of covariance matrices, and over more general classes. Furthermore, it correctly recovers the bandwidth when the true covariance is exactly banded. Our convex formulation admits a simple and efficient algorithm. Empirical studies demonstrate its practical effectiveness and illustrate that our exactly-banded estimator works well even when the true covariance matrix is only close to a banded matrix, confirming our theoretical results. Our method compares favorably with all existing methods, in terms of accuracy and speed. We illustrate the practical merits of the convex banding estimator by showing that it can be used to improve the performance of discriminant analysis for classifying sound recordings.

Tensor-GMRES method for large sparse systems of nonlinear equations

Science.gov (United States)

Feng, Dan; Pulliam, Thomas H.

1994-01-01

This paper introduces a tensor-Krylov method, the tensor-GMRES method, for large sparse systems of nonlinear equations. This method is a coupling of tensor model formation and solution techniques for nonlinear equations with Krylov subspace projection techniques for unsymmetric systems of linear equations. Traditional tensor methods for nonlinear equations are based on a quadratic model of the nonlinear function, a standard linear model augmented by a simple second order term. These methods are shown to be significantly more efficient than standard methods both on nonsingular problems and on problems where the Jacobian matrix at the solution is singular. A major disadvantage of the traditional tensor methods is that the solution of the tensor model requires the factorization of the Jacobian matrix, which may not be suitable for problems where the Jacobian matrix is large and has a 'bad' sparsity structure for an efficient factorization. We overcome this difficulty by forming and solving the tensor model using an extension of a Newton-GMRES scheme. Like traditional tensor methods, we show that the new tensor method has significant computational advantages over the analogous Newton counterpart. Consistent with Krylov subspace based methods, the new tensor method does not depend on the factorization of the Jacobian matrix. As a matter of fact, the Jacobian matrix is never needed explicitly.

SLAP, Large Sparse Linear System Solution Package

International Nuclear Information System (INIS)

Greenbaum, A.

1987-01-01

1 - Description of program or function: SLAP is a set of routines for solving large sparse systems of linear equations. One need not store the entire matrix - only the nonzero elements and their row and column numbers. Any nonzero structure is acceptable, so the linear system solver need not be modified when the structure of the matrix changes. Auxiliary storage space is acquired and released within the routines themselves by use of the LRLTRAN POINTER statement. 2 - Method of solution: SLAP contains one direct solver, a band matrix factorization and solution routine, BAND, and several interactive solvers. The iterative routines are as follows: JACOBI, Jacobi iteration; GS, Gauss-Seidel Iteration; ILUIR, incomplete LU decomposition with iterative refinement; DSCG and ICCG, diagonal scaling and incomplete Cholesky decomposition with conjugate gradient iteration (for symmetric positive definite matrices only); DSCGN and ILUGGN, diagonal scaling and incomplete LU decomposition with conjugate gradient interaction on the normal equations; DSBCG and ILUBCG, diagonal scaling and incomplete LU decomposition with bi-conjugate gradient iteration; and DSOMN and ILUOMN, diagonal scaling and incomplete LU decomposition with ORTHOMIN iteration

Rotational image deblurring with sparse matrices

DEFF Research Database (Denmark)

Hansen, Per Christian; Nagy, James G.; Tigkos, Konstantinos

2014-01-01

We describe iterative deblurring algorithms that can handle blur caused by a rotation along an arbitrary axis (including the common case of pure rotation). Our algorithms use a sparse-matrix representation of the blurring operation, which allows us to easily handle several different boundary...

Solving sparse linear least squares problems on some supercomputers by using large dense blocks

DEFF Research Database (Denmark)

Hansen, Per Christian; Ostromsky, T; Sameh, A

1997-01-01

technique is preferable to sparse matrix technique when the matrices are not large, because the high computational speed compensates fully the disadvantages of using more arithmetic operations and more storage. For very large matrices the computations must be organized as a sequence of tasks in each......Efficient subroutines for dense matrix computations have recently been developed and are available on many high-speed computers. On some computers the speed of many dense matrix operations is near to the peak-performance. For sparse matrices storage and operations can be saved by operating only...... and storing only nonzero elements. However, the price is a great degradation of the speed of computations on supercomputers (due to the use of indirect addresses, to the need to insert new nonzeros in the sparse storage scheme, to the lack of data locality, etc.). On many high-speed computers a dense matrix...

Ordering sparse matrices for cache-based systems

International Nuclear Information System (INIS)

Biswas, Rupak; Oliker, Leonid

2001-01-01

The Conjugate Gradient (CG) algorithm is the oldest and best-known Krylov subspace method used to solve sparse linear systems. Most of the coating-point operations within each CG iteration is spent performing sparse matrix-vector multiplication (SPMV). We examine how various ordering and partitioning strategies affect the performance of CG and SPMV when different programming paradigms are used on current commercial cache-based computers. However, a multithreaded implementation on the cacheless Cray MTA demonstrates high efficiency and scalability without any special ordering or partitioning

Sparse linear systems: Theory of decomposition, methods, technology, applications and implementation in Wolfram Mathematica

Energy Technology Data Exchange (ETDEWEB)

Pilipchuk, L. A., E-mail: pilipchik@bsu.by [Belarussian State University, 220030 Minsk, 4, Nezavisimosti avenue, Republic of Belarus (Belarus); Pilipchuk, A. S., E-mail: an.pilipchuk@gmail.com [The Natural Resources and Environmental Protestion Ministry of the Republic of Belarus, 220004 Minsk, 10 Kollektornaya Street, Republic of Belarus (Belarus)

2015-11-30

In this paper we propose the theory of decomposition, methods, technologies, applications and implementation in Wol-fram Mathematica for the constructing the solutions of the sparse linear systems. One of the applications is the Sensor Location Problem for the symmetric graph in the case when split ratios of some arc flows can be zeros. The objective of that application is to minimize the number of sensors that are assigned to the nodes. We obtain a sparse system of linear algebraic equations and research its matrix rank. Sparse systems of these types appear in generalized network flow programming problems in the form of restrictions and can be characterized as systems with a large sparse sub-matrix representing the embedded network structure.

Sparse linear systems: Theory of decomposition, methods, technology, applications and implementation in Wolfram Mathematica

International Nuclear Information System (INIS)

Pilipchuk, L. A.; Pilipchuk, A. S.

2015-01-01

In this paper we propose the theory of decomposition, methods, technologies, applications and implementation in Wol-fram Mathematica for the constructing the solutions of the sparse linear systems. One of the applications is the Sensor Location Problem for the symmetric graph in the case when split ratios of some arc flows can be zeros. The objective of that application is to minimize the number of sensors that are assigned to the nodes. We obtain a sparse system of linear algebraic equations and research its matrix rank. Sparse systems of these types appear in generalized network flow programming problems in the form of restrictions and can be characterized as systems with a large sparse sub-matrix representing the embedded network structure

Simulation of sparse matrix array designs

Science.gov (United States)

Boehm, Rainer; Heckel, Thomas

2018-04-01

Matrix phased array probes are becoming more prominently used in industrial applications. The main drawbacks, using probes incorporating a very large number of transducer elements, are needed for an appropriate cabling and an ultrasonic device offering many parallel channels. Matrix arrays designed for extended functionality feature at least 64 or more elements. Typical arrangements are square matrices, e.g., 8 by 8 or 11 by 11 or rectangular matrixes, e.g., 8 by 16 or 10 by 12 to fit a 128-channel phased array system. In some phased array systems, the number of simultaneous active elements is limited to a certain number, e.g., 32 or 64. Those setups do not allow running the probe with all elements active, which may cause a significant change in the directivity pattern of the resulting sound beam. When only a subset of elements can be used during a single acquisition, different strategies may be applied to collect enough data for rebuilding the missing information from the echo signal. Omission of certain elements may be one approach, overlay of subsequent shots with different active areas may be another one. This paper presents the influence of a decreased number of active elements on the sound field and their distribution on the array. Solutions using subsets with different element activity patterns on matrix arrays and their advantages and disadvantages concerning the sound field are evaluated using semi-analytical simulation tools. Sound field criteria are discussed, which are significant for non-destructive testing results and for the system setup.

Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition

Science.gov (United States)

Tang, Xin; Feng, Guo-can; Li, Xiao-xin; Cai, Jia-xin

2015-01-01

Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC) achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC). Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis) of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our method achieves the

Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition.

Science.gov (United States)

Tang, Xin; Feng, Guo-Can; Li, Xiao-Xin; Cai, Jia-Xin

2015-01-01

Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC) achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC). Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis) of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our method achieves the

Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition.

Directory of Open Access Journals (Sweden)

Xin Tang

Full Text Available Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC. Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our

The application of sparse linear prediction dictionary to compressive sensing in speech signals

Directory of Open Access Journals (Sweden)

YOU Hanxu

2016-04-01

Full Text Available Appling compressive sensing (CS,which theoretically guarantees that signal sampling and signal compression can be achieved simultaneously,into audio and speech signal processing is one of the most popular research topics in recent years.In this paper,K-SVD algorithm was employed to learn a sparse linear prediction dictionary regarding as the sparse basis of underlying speech signals.Compressed signals was obtained by applying random Gaussian matrix to sample original speech frames.Orthogonal matching pursuit (OMP and compressive sampling matching pursuit (CoSaMP were adopted to recovery original signals from compressed one.Numbers of experiments were carried out to investigate the impact of speech frames length,compression ratios,sparse basis and reconstruction algorithms on CS performance.Results show that sparse linear prediction dictionary can advance the performance of speech signals reconstruction compared with discrete cosine transform (DCT matrix.

Convex nonnegative matrix factorization with manifold regularization.

Science.gov (United States)

Hu, Wenjun; Choi, Kup-Sze; Wang, Peiliang; Jiang, Yunliang; Wang, Shitong

2015-03-01

Nonnegative Matrix Factorization (NMF) has been extensively applied in many areas, including computer vision, pattern recognition, text mining, and signal processing. However, nonnegative entries are usually required for the data matrix in NMF, which limits its application. Besides, while the basis and encoding vectors obtained by NMF can represent the original data in low dimension, the representations do not always reflect the intrinsic geometric structure embedded in the data. Motivated by manifold learning and Convex NMF (CNMF), we propose a novel matrix factorization method called Graph Regularized and Convex Nonnegative Matrix Factorization (GCNMF) by introducing a graph regularized term into CNMF. The proposed matrix factorization technique not only inherits the intrinsic low-dimensional manifold structure, but also allows the processing of mixed-sign data matrix. Clustering experiments on nonnegative and mixed-sign real-world data sets are conducted to demonstrate the effectiveness of the proposed method. Copyright © 2014 Elsevier Ltd. All rights reserved.

Balanced and sparse Tamo-Barg codes

KAUST Repository

Halbawi, Wael; Duursma, Iwan; Dau, Hoang; Hassibi, Babak

2017-01-01

We construct balanced and sparse generator matrices for Tamo and Barg's Locally Recoverable Codes (LRCs). More specifically, for a cyclic Tamo-Barg code of length n, dimension k and locality r, we show how to deterministically construct a generator matrix where the number of nonzeros in any two columns differs by at most one, and where the weight of every row is d + r - 1, where d is the minimum distance of the code. Since LRCs are designed mainly for distributed storage systems, the results presented in this work provide a computationally balanced and efficient encoding scheme for these codes. The balanced property ensures that the computational effort exerted by any storage node is essentially the same, whilst the sparse property ensures that this effort is minimal. The work presented in this paper extends a similar result previously established for Reed-Solomon (RS) codes, where it is now known that any cyclic RS code possesses a generator matrix that is balanced as described, but is sparsest, meaning that each row has d nonzeros.

Balanced and sparse Tamo-Barg codes

KAUST Repository

Halbawi, Wael

2017-08-29

We construct balanced and sparse generator matrices for Tamo and Barg\\'s Locally Recoverable Codes (LRCs). More specifically, for a cyclic Tamo-Barg code of length n, dimension k and locality r, we show how to deterministically construct a generator matrix where the number of nonzeros in any two columns differs by at most one, and where the weight of every row is d + r - 1, where d is the minimum distance of the code. Since LRCs are designed mainly for distributed storage systems, the results presented in this work provide a computationally balanced and efficient encoding scheme for these codes. The balanced property ensures that the computational effort exerted by any storage node is essentially the same, whilst the sparse property ensures that this effort is minimal. The work presented in this paper extends a similar result previously established for Reed-Solomon (RS) codes, where it is now known that any cyclic RS code possesses a generator matrix that is balanced as described, but is sparsest, meaning that each row has d nonzeros.

M3: Matrix Multiplication on MapReduce

DEFF Research Database (Denmark)

Silvestri, Francesco; Ceccarello, Matteo

2015-01-01

M3 is an Hadoop library for performing dense and sparse matrix multiplication in MapReduce. The library is based on multi-round algorithms exploiting the 3D decomposition of the problem.......M3 is an Hadoop library for performing dense and sparse matrix multiplication in MapReduce. The library is based on multi-round algorithms exploiting the 3D decomposition of the problem....

Reconstruction of sparse connectivity in neural networks from spike train covariances

International Nuclear Information System (INIS)

Pernice, Volker; Rotter, Stefan

2013-01-01

The inference of causation from correlation is in general highly problematic. Correspondingly, it is difficult to infer the existence of physical synaptic connections between neurons from correlations in their activity. Covariances in neural spike trains and their relation to network structure have been the subject of intense research, both experimentally and theoretically. The influence of recurrent connections on covariances can be characterized directly in linear models, where connectivity in the network is described by a matrix of linear coupling kernels. However, as indirect connections also give rise to covariances, the inverse problem of inferring network structure from covariances can generally not be solved unambiguously. Here we study to what degree this ambiguity can be resolved if the sparseness of neural networks is taken into account. To reconstruct a sparse network, we determine the minimal set of linear couplings consistent with the measured covariances by minimizing the L 1 norm of the coupling matrix under appropriate constraints. Contrary to intuition, after stochastic optimization of the coupling matrix, the resulting estimate of the underlying network is directed, despite the fact that a symmetric matrix of count covariances is used for inference. The performance of the new method is best if connections are neither exceedingly sparse, nor too dense, and it is easily applicable for networks of a few hundred nodes. Full coupling kernels can be obtained from the matrix of full covariance functions. We apply our method to networks of leaky integrate-and-fire neurons in an asynchronous–irregular state, where spike train covariances are well described by a linear model. (paper)

Fast alternating projected gradient descent algorithms for recovering spectrally sparse signals

KAUST Repository

Cho, Myung

2016-06-24

We propose fast algorithms that speed up or improve the performance of recovering spectrally sparse signals from un-derdetermined measurements. Our algorithms are based on a non-convex approach of using alternating projected gradient descent for structured matrix recovery. We apply this approach to two formulations of structured matrix recovery: Hankel and Toeplitz mosaic structured matrix, and Hankel structured matrix. Our methods provide better recovery performance, and faster signal recovery than existing algorithms, including atomic norm minimization.

Fast alternating projected gradient descent algorithms for recovering spectrally sparse signals

KAUST Repository

Cho, Myung; Cai, Jian-Feng; Liu, Suhui; Eldar, Yonina C.; Xu, Weiyu

2016-01-01

We propose fast algorithms that speed up or improve the performance of recovering spectrally sparse signals from un-derdetermined measurements. Our algorithms are based on a non-convex approach of using alternating projected gradient descent for structured matrix recovery. We apply this approach to two formulations of structured matrix recovery: Hankel and Toeplitz mosaic structured matrix, and Hankel structured matrix. Our methods provide better recovery performance, and faster signal recovery than existing algorithms, including atomic norm minimization.

P-SPARSLIB: A parallel sparse iterative solution package

Energy Technology Data Exchange (ETDEWEB)

Saad, Y. [Univ. of Minnesota, Minneapolis, MN (United States)

1994-12-31

Iterative methods are gaining popularity in engineering and sciences at a time where the computational environment is changing rapidly. P-SPARSLIB is a project to build a software library for sparse matrix computations on parallel computers. The emphasis is on iterative methods and the use of distributed sparse matrices, an extension of the domain decomposition approach to general sparse matrices. One of the goals of this project is to develop a software package geared towards specific applications. For example, the author will test the performance and usefulness of P-SPARSLIB modules on linear systems arising from CFD applications. Equally important is the goal of portability. In the long run, the author wishes to ensure that this package is portable on a variety of platforms, including SIMD environments and shared memory environments.

A new scheduling algorithm for parallel sparse LU factorization with static pivoting

Energy Technology Data Exchange (ETDEWEB)

Grigori, Laura; Li, Xiaoye S.

2002-08-20

In this paper we present a static scheduling algorithm for parallel sparse LU factorization with static pivoting. The algorithm is divided into mapping and scheduling phases, using the symmetric pruned graphs of L' and U to represent dependencies. The scheduling algorithm is designed for driving the parallel execution of the factorization on a distributed-memory architecture. Experimental results and comparisons with SuperLU{_}DIST are reported after applying this algorithm on real world application matrices on an IBM SP RS/6000 distributed memory machine.

A Sparse Approximate Inverse Preconditioner for Nonsymmetric Linear Systems

Czech Academy of Sciences Publication Activity Database

Benzi, M.; Tůma, Miroslav

1998-01-01

Roč. 19, č. 3 (1998), s. 968-994 ISSN 1064-8275 R&D Projects: GA ČR GA201/93/0067; GA AV ČR IAA230401 Keywords : large sparse systems * interative methods * preconditioning * approximate inverse * sparse linear systems * sparse matrices * incomplete factorizations * conjugate gradient -type methods Subject RIV: BA - General Mathematics Impact factor: 1.378, year: 1998

Low-Rank Matrix Factorization With Adaptive Graph Regularizer.

Science.gov (United States)

Lu, Gui-Fu; Wang, Yong; Zou, Jian

2016-05-01

In this paper, we present a novel low-rank matrix factorization algorithm with adaptive graph regularizer (LMFAGR). We extend the recently proposed low-rank matrix with manifold regularization (MMF) method with an adaptive regularizer. Different from MMF, which constructs an affinity graph in advance, LMFAGR can simultaneously seek graph weight matrix and low-dimensional representations of data. That is, graph construction and low-rank matrix factorization are incorporated into a unified framework, which results in an automatically updated graph rather than a predefined one. The experimental results on some data sets demonstrate that the proposed algorithm outperforms the state-of-the-art low-rank matrix factorization methods.

Combinatorial Algorithms for Computing Column Space Bases ThatHave Sparse Inverses

Energy Technology Data Exchange (ETDEWEB)

Pinar, Ali; Chow, Edmond; Pothen, Alex

2005-03-18

This paper presents a combinatorial study on the problem ofconstructing a sparse basis forthe null-space of a sparse, underdetermined, full rank matrix, A. Such a null-space is suitable forsolving solving many saddle point problems. Our approach is to form acolumn space basis of A that has a sparse inverse, by selecting suitablecolumns of A. This basis is then used to form a sparse null-space basisin fundamental form. We investigate three different algorithms forcomputing the column space basis: Two greedy approaches that rely onmatching, and a third employing a divide and conquer strategy implementedwith hypergraph partitioning followed by the greedy approach. We alsodiscuss the complexity of selecting a column basis when it is known thata block diagonal basis exists with a small given block size.

Salient Object Detection via Structured Matrix Decomposition.

Science.gov (United States)

Peng, Houwen; Li, Bing; Ling, Haibin; Hu, Weiming; Xiong, Weihua; Maybank, Stephen J

2016-05-04

Low-rank recovery models have shown potential for salient object detection, where a matrix is decomposed into a low-rank matrix representing image background and a sparse matrix identifying salient objects. Two deficiencies, however, still exist. First, previous work typically assumes the elements in the sparse matrix are mutually independent, ignoring the spatial and pattern relations of image regions. Second, when the low-rank and sparse matrices are relatively coherent, e.g., when there are similarities between the salient objects and background or when the background is complicated, it is difficult for previous models to disentangle them. To address these problems, we propose a novel structured matrix decomposition model with two structural regularizations: (1) a tree-structured sparsity-inducing regularization that captures the image structure and enforces patches from the same object to have similar saliency values, and (2) a Laplacian regularization that enlarges the gaps between salient objects and the background in feature space. Furthermore, high-level priors are integrated to guide the matrix decomposition and boost the detection. We evaluate our model for salient object detection on five challenging datasets including single object, multiple objects and complex scene images, and show competitive results as compared with 24 state-of-the-art methods in terms of seven performance metrics.

Multiple-Factor Based Sparse Urban Travel Time Prediction

Directory of Open Access Journals (Sweden)

Xinyan Zhu

2018-02-01

Full Text Available The prediction of travel time is challenging given the sparseness of real-time traffic data and the uncertainty of travel, because it is influenced by multiple factors on the congested urban road networks. In our paper, we propose a three-layer neural network from big probe vehicles data incorporating multi-factors to estimate travel time. The procedure includes the following three steps. First, we aggregate data according to the travel time of a single taxi traveling a target link on working days as traffic flows display similar traffic patterns over a weekly cycle. We then extract feature relationships between target and adjacent links at 30 min interval. About 224,830,178 records are extracted from probe vehicles. Second, we design a three-layer artificial neural network model. The number of neurons in input layer is eight, and the number of neurons in output layer is one. Finally, the trained neural network model is used for link travel time prediction. Different factors are included to examine their influence on the link travel time. Our model is verified using historical data from probe vehicles collected from May to July 2014 in Wuhan, China. The results show that we could obtain the link travel time prediction results using the designed artificial neural network model and detect the influence of different factors on link travel time.

A preconditioned inexact newton method for nonlinear sparse electromagnetic imaging

KAUST Repository

Desmal, Abdulla

2015-03-01

A nonlinear inversion scheme for the electromagnetic microwave imaging of domains with sparse content is proposed. Scattering equations are constructed using a contrast-source (CS) formulation. The proposed method uses an inexact Newton (IN) scheme to tackle the nonlinearity of these equations. At every IN iteration, a system of equations, which involves the Frechet derivative (FD) matrix of the CS operator, is solved for the IN step. A sparsity constraint is enforced on the solution via thresholded Landweber iterations, and the convergence is significantly increased using a preconditioner that levels the FD matrix\\'s singular values associated with contrast and equivalent currents. To increase the accuracy, the weight of the regularization\\'s penalty term is reduced during the IN iterations consistently with the scheme\\'s quadratic convergence. At the end of each IN iteration, an additional thresholding, which removes small \\'ripples\\' that are produced by the IN step, is applied to maintain the solution\\'s sparsity. Numerical results demonstrate the applicability of the proposed method in recovering sparse and discontinuous dielectric profiles with high contrast values.

Speculative segmented sum for sparse matrix-vector multiplication on heterogeneous processors

DEFF Research Database (Denmark)

Liu, Weifeng; Vinter, Brian

2015-01-01

of the same chip is triggered to re-arrange the predicted partial sums for a correct resulting vector. On three heterogeneous processors from Intel, AMD and nVidia, using 20 sparse matrices as a benchmark suite, the experimental results show that our method obtains significant performance improvement over...

Enhancing Scalability of Sparse Direct Methods

International Nuclear Information System (INIS)

Li, Xiaoye S.; Demmel, James; Grigori, Laura; Gu, Ming; Xia, Jianlin; Jardin, Steve; Sovinec, Carl; Lee, Lie-Quan

2007-01-01

TOPS is providing high-performance, scalable sparse direct solvers, which have had significant impacts on the SciDAC applications, including fusion simulation (CEMM), accelerator modeling (COMPASS), as well as many other mission-critical applications in DOE and elsewhere. Our recent developments have been focusing on new techniques to overcome scalability bottleneck of direct methods, in both time and memory. These include parallelizing symbolic analysis phase and developing linear-complexity sparse factorization methods. The new techniques will make sparse direct methods more widely usable in large 3D simulations on highly-parallel petascale computers

Nonnegative Matrix Factorizations Performing Object Detection and Localization

Directory of Open Access Journals (Sweden)

G. Casalino

2012-01-01

Full Text Available We study the problem of detecting and localizing objects in still, gray-scale images making use of the part-based representation provided by nonnegative matrix factorizations. Nonnegative matrix factorization represents an emerging example of subspace methods, which is able to extract interpretable parts from a set of template image objects and then to additively use them for describing individual objects. In this paper, we present a prototype system based on some nonnegative factorization algorithms, which differ in the additional properties added to the nonnegative representation of data, in order to investigate if any additional constraint produces better results in general object detection via nonnegative matrix factorizations.

Low-Rank Sparse Coding for Image Classification

KAUST Repository

Zhang, Tianzhu; Ghanem, Bernard; Liu, Si; Xu, Changsheng; Ahuja, Narendra

2013-01-01

In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of code words. As such, it casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding.

Low-Rank Sparse Coding for Image Classification

KAUST Repository

Zhang, Tianzhu

2013-12-01

In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of code words. As such, it casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding.

Sparse Probabilistic Parallel Factor Analysis for the Modeling of PET and Task-fMRI Data

DEFF Research Database (Denmark)

Beliveau, Vincent; Papoutsakis, Georgios; Hinrich, Jesper Løve

2017-01-01

Modern datasets are often multiway in nature and can contain patterns common to a mode of the data (e.g. space, time, and subjects). Multiway decomposition such as parallel factor analysis (PARAFAC) take into account the intrinsic structure of the data, and sparse versions of these methods improv...

Sparse multivariate factor analysis regression models and its applications to integrative genomics analysis.

Science.gov (United States)

Zhou, Yan; Wang, Pei; Wang, Xianlong; Zhu, Ji; Song, Peter X-K

2017-01-01

The multivariate regression model is a useful tool to explore complex associations between two kinds of molecular markers, which enables the understanding of the biological pathways underlying disease etiology. For a set of correlated response variables, accounting for such dependency can increase statistical power. Motivated by integrative genomic data analyses, we propose a new methodology-sparse multivariate factor analysis regression model (smFARM), in which correlations of response variables are assumed to follow a factor analysis model with latent factors. This proposed method not only allows us to address the challenge that the number of association parameters is larger than the sample size, but also to adjust for unobserved genetic and/or nongenetic factors that potentially conceal the underlying response-predictor associations. The proposed smFARM is implemented by the EM algorithm and the blockwise coordinate descent algorithm. The proposed methodology is evaluated and compared to the existing methods through extensive simulation studies. Our results show that accounting for latent factors through the proposed smFARM can improve sensitivity of signal detection and accuracy of sparse association map estimation. We illustrate smFARM by two integrative genomics analysis examples, a breast cancer dataset, and an ovarian cancer dataset, to assess the relationship between DNA copy numbers and gene expression arrays to understand genetic regulatory patterns relevant to the disease. We identify two trans-hub regions: one in cytoband 17q12 whose amplification influences the RNA expression levels of important breast cancer genes, and the other in cytoband 9q21.32-33, which is associated with chemoresistance in ovarian cancer. © 2016 WILEY PERIODICALS, INC.

On-Chip Neural Data Compression Based On Compressed Sensing With Sparse Sensing Matrices.

Science.gov (United States)

Zhao, Wenfeng; Sun, Biao; Wu, Tong; Yang, Zhi

2018-02-01

On-chip neural data compression is an enabling technique for wireless neural interfaces that suffer from insufficient bandwidth and power budgets to transmit the raw data. The data compression algorithm and its implementation should be power and area efficient and functionally reliable over different datasets. Compressed sensing is an emerging technique that has been applied to compress various neurophysiological data. However, the state-of-the-art compressed sensing (CS) encoders leverage random but dense binary measurement matrices, which incur substantial implementation costs on both power and area that could offset the benefits from the reduced wireless data rate. In this paper, we propose two CS encoder designs based on sparse measurement matrices that could lead to efficient hardware implementation. Specifically, two different approaches for the construction of sparse measurement matrices, i.e., the deterministic quasi-cyclic array code (QCAC) matrix and -sparse random binary matrix [-SRBM] are exploited. We demonstrate that the proposed CS encoders lead to comparable recovery performance. And efficient VLSI architecture designs are proposed for QCAC-CS and -SRBM encoders with reduced area and total power consumption.

A Matrix Splitting Method for Composite Function Minimization

KAUST Repository

Yuan, Ganzhao

2016-12-07

Composite function minimization captures a wide spectrum of applications in both computer vision and machine learning. It includes bound constrained optimization and cardinality regularized optimization as special cases. This paper proposes and analyzes a new Matrix Splitting Method (MSM) for minimizing composite functions. It can be viewed as a generalization of the classical Gauss-Seidel method and the Successive Over-Relaxation method for solving linear systems in the literature. Incorporating a new Gaussian elimination procedure, the matrix splitting method achieves state-of-the-art performance. For convex problems, we establish the global convergence, convergence rate, and iteration complexity of MSM, while for non-convex problems, we prove its global convergence. Finally, we validate the performance of our matrix splitting method on two particular applications: nonnegative matrix factorization and cardinality regularized sparse coding. Extensive experiments show that our method outperforms existing composite function minimization techniques in term of both efficiency and efficacy.

A Matrix Splitting Method for Composite Function Minimization

KAUST Repository

Yuan, Ganzhao; Zheng, Wei-Shi; Ghanem, Bernard

2016-01-01

Composite function minimization captures a wide spectrum of applications in both computer vision and machine learning. It includes bound constrained optimization and cardinality regularized optimization as special cases. This paper proposes and analyzes a new Matrix Splitting Method (MSM) for minimizing composite functions. It can be viewed as a generalization of the classical Gauss-Seidel method and the Successive Over-Relaxation method for solving linear systems in the literature. Incorporating a new Gaussian elimination procedure, the matrix splitting method achieves state-of-the-art performance. For convex problems, we establish the global convergence, convergence rate, and iteration complexity of MSM, while for non-convex problems, we prove its global convergence. Finally, we validate the performance of our matrix splitting method on two particular applications: nonnegative matrix factorization and cardinality regularized sparse coding. Extensive experiments show that our method outperforms existing composite function minimization techniques in term of both efficiency and efficacy.

Exploiting Data Sparsity for Large-Scale Matrix Computations

KAUST Repository

Akbudak, Kadir

2018-02-24

Exploiting data sparsity in dense matrices is an algorithmic bridge between architectures that are increasingly memory-austere on a per-core basis and extreme-scale applications. The Hierarchical matrix Computations on Manycore Architectures (HiCMA) library tackles this challenging problem by achieving significant reductions in time to solution and memory footprint, while preserving a specified accuracy requirement of the application. HiCMA provides a high-performance implementation on distributed-memory systems of one of the most widely used matrix factorization in large-scale scientific applications, i.e., the Cholesky factorization. It employs the tile low-rank data format to compress the dense data-sparse off-diagonal tiles of the matrix. It then decomposes the matrix computations into interdependent tasks and relies on the dynamic runtime system StarPU for asynchronous out-of-order scheduling, while allowing high user-productivity. Performance comparisons and memory footprint on matrix dimensions up to eleven million show a performance gain and memory saving of more than an order of magnitude for both metrics on thousands of cores, against state-of-the-art open-source and vendor optimized numerical libraries. This represents an important milestone in enabling large-scale matrix computations toward solving big data problems in geospatial statistics for climate/weather forecasting applications.

Exploiting Data Sparsity for Large-Scale Matrix Computations

KAUST Repository

Akbudak, Kadir; Ltaief, Hatem; Mikhalev, Aleksandr; Charara, Ali; Keyes, David E.

2018-01-01

Exploiting data sparsity in dense matrices is an algorithmic bridge between architectures that are increasingly memory-austere on a per-core basis and extreme-scale applications. The Hierarchical matrix Computations on Manycore Architectures (HiCMA) library tackles this challenging problem by achieving significant reductions in time to solution and memory footprint, while preserving a specified accuracy requirement of the application. HiCMA provides a high-performance implementation on distributed-memory systems of one of the most widely used matrix factorization in large-scale scientific applications, i.e., the Cholesky factorization. It employs the tile low-rank data format to compress the dense data-sparse off-diagonal tiles of the matrix. It then decomposes the matrix computations into interdependent tasks and relies on the dynamic runtime system StarPU for asynchronous out-of-order scheduling, while allowing high user-productivity. Performance comparisons and memory footprint on matrix dimensions up to eleven million show a performance gain and memory saving of more than an order of magnitude for both metrics on thousands of cores, against state-of-the-art open-source and vendor optimized numerical libraries. This represents an important milestone in enabling large-scale matrix computations toward solving big data problems in geospatial statistics for climate/weather forecasting applications.

Convergence Improvement of Response Matrix Method with Large Discontinuity Factors

International Nuclear Information System (INIS)

Yamamoto, Akio

2003-01-01

In the response matrix method, a numerical divergence problem has been reported when extremely small or large discontinuity factors are utilized in the calculations. In this paper, an alternative response matrix formulation to solve the divergence problem is discussed, and properties of iteration matrixes are investigated through eigenvalue analyses. In the conventional response matrix formulation, partial currents between adjacent nodes are assumed to be discontinuous, and outgoing partial currents are converted into incoming partial currents by the discontinuity factor matrix. Namely, the partial currents of the homogeneous system (i.e., homogeneous partial currents) are treated in the conventional response matrix formulation. In this approach, the spectral radius of an iteration matrix for the partial currents may exceed unity when an extremely small or large discontinuity factor is used. Contrary to this, an alternative response matrix formulation using heterogeneous partial currents is discussed in this paper. In the latter approach, partial currents are assumed to be continuous between adjacent nodes, and discontinuity factors are directly considered in the coefficients of a response matrix. From the eigenvalue analysis of the iteration matrix for the one-group, one-dimensional problem, the spectral radius for the heterogeneous partial current formulation does not exceed unity even if an extremely small or large discontinuity factor is used in the calculation; numerical stability of the alternative formulation is superior to the conventional one. The numerical stability of the heterogeneous partial current formulation is also confirmed by the two-dimensional light water reactor core analysis. Since the heterogeneous partial current formulation does not require any approximation, the converged solution exactly reproduces the reference solution when the discontinuity factors are directly derived from the reference calculation

Sparse Representation Denoising for Radar High Resolution Range Profiling

Directory of Open Access Journals (Sweden)

Min Li

2014-01-01

Full Text Available Radar high resolution range profile has attracted considerable attention in radar automatic target recognition. In practice, radar return is usually contaminated by noise, which results in profile distortion and recognition performance degradation. To deal with this problem, in this paper, a novel denoising method based on sparse representation is proposed to remove the Gaussian white additive noise. The return is sparsely described in the Fourier redundant dictionary and the denoising problem is described as a sparse representation model. Noise level of the return, which is crucial to the denoising performance but often unknown, is estimated by performing subspace method on the sliding subsequence correlation matrix. Sliding window process enables noise level estimation using only one observation sequence, not only guaranteeing estimation efficiency but also avoiding the influence of profile time-shift sensitivity. Experimental results show that the proposed method can effectively improve the signal-to-noise ratio of the return, leading to a high-quality profile.

Using Chebyshev polynomials and approximate inverse triangular factorizations for preconditioning the conjugate gradient method

Science.gov (United States)

Kaporin, I. E.

2012-02-01

In order to precondition a sparse symmetric positive definite matrix, its approximate inverse is examined, which is represented as the product of two sparse mutually adjoint triangular matrices. In this way, the solution of the corresponding system of linear algebraic equations (SLAE) by applying the preconditioned conjugate gradient method (CGM) is reduced to performing only elementary vector operations and calculating sparse matrix-vector products. A method for constructing the above preconditioner is described and analyzed. The triangular factor has a fixed sparsity pattern and is optimal in the sense that the preconditioned matrix has a minimum K-condition number. The use of polynomial preconditioning based on Chebyshev polynomials makes it possible to considerably reduce the amount of scalar product operations (at the cost of an insignificant increase in the total number of arithmetic operations). The possibility of an efficient massively parallel implementation of the resulting method for solving SLAEs is discussed. For a sequential version of this method, the results obtained by solving 56 test problems from the Florida sparse matrix collection (which are large-scale and ill-conditioned) are presented. These results show that the method is highly reliable and has low computational costs.

Large-region acoustic source mapping using a movable array and sparse covariance fitting.

Science.gov (United States)

Zhao, Shengkui; Tuna, Cagdas; Nguyen, Thi Ngoc Tho; Jones, Douglas L

2017-01-01

Large-region acoustic source mapping is important for city-scale noise monitoring. Approaches using a single-position measurement scheme to scan large regions using small arrays cannot provide clean acoustic source maps, while deploying large arrays spanning the entire region of interest is prohibitively expensive. A multiple-position measurement scheme is applied to scan large regions at multiple spatial positions using a movable array of small size. Based on the multiple-position measurement scheme, a sparse-constrained multiple-position vectorized covariance matrix fitting approach is presented. In the proposed approach, the overall sample covariance matrix of the incoherent virtual array is first estimated using the multiple-position array data and then vectorized using the Khatri-Rao (KR) product. A linear model is then constructed for fitting the vectorized covariance matrix and a sparse-constrained reconstruction algorithm is proposed for recovering source powers from the model. The user parameter settings are discussed. The proposed approach is tested on a 30 m × 40 m region and a 60 m × 40 m region using simulated and measured data. Much cleaner acoustic source maps and lower sound pressure level errors are obtained compared to the beamforming approaches and the previous sparse approach [Zhao, Tuna, Nguyen, and Jones, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP) (2016)].

A Rank-Constrained Matrix Representation for Hypergraph-Based Subspace Clustering

Directory of Open Access Journals (Sweden)

Yubao Sun

2015-01-01

Full Text Available This paper presents a novel, rank-constrained matrix representation combined with hypergraph spectral analysis to enable the recovery of the original subspace structures of corrupted data. Real-world data are frequently corrupted with both sparse error and noise. Our matrix decomposition model separates the low-rank, sparse error, and noise components from the data in order to enhance robustness to the corruption. In order to obtain the desired rank representation of the data within a dictionary, our model directly utilizes rank constraints by restricting the upper bound of the rank range. An alternative projection algorithm is proposed to estimate the low-rank representation and separate the sparse error from the data matrix. To further capture the complex relationship between data distributed in multiple subspaces, we use hypergraph to represent the data by encapsulating multiple related samples into one hyperedge. The final clustering result is obtained by spectral decomposition of the hypergraph Laplacian matrix. Validation experiments on the Extended Yale Face Database B, AR, and Hopkins 155 datasets show that the proposed method is a promising tool for subspace clustering.

Supervised Transfer Sparse Coding

KAUST Repository

Al-Shedivat, Maruan

2014-07-27

A combination of the sparse coding and transfer learn- ing techniques was shown to be accurate and robust in classification tasks where training and testing objects have a shared feature space but are sampled from differ- ent underlying distributions, i.e., belong to different do- mains. The key assumption in such case is that in spite of the domain disparity, samples from different domains share some common hidden factors. Previous methods often assumed that all the objects in the target domain are unlabeled, and thus the training set solely comprised objects from the source domain. However, in real world applications, the target domain often has some labeled objects, or one can always manually label a small num- ber of them. In this paper, we explore such possibil- ity and show how a small number of labeled data in the target domain can significantly leverage classifica- tion accuracy of the state-of-the-art transfer sparse cod- ing methods. We further propose a unified framework named supervised transfer sparse coding (STSC) which simultaneously optimizes sparse representation, domain transfer and classification. Experimental results on three applications demonstrate that a little manual labeling and then learning the model in a supervised fashion can significantly improve classification accuracy.

High-dimensional statistical inference: From vector to matrix

Science.gov (United States)

Zhang, Anru

Statistical inference for sparse signals or low-rank matrices in high-dimensional settings is of significant interest in a range of contemporary applications. It has attracted significant recent attention in many fields including statistics, applied mathematics and electrical engineering. In this thesis, we consider several problems in including sparse signal recovery (compressed sensing under restricted isometry) and low-rank matrix recovery (matrix recovery via rank-one projections and structured matrix completion). The first part of the thesis discusses compressed sensing and affine rank minimization in both noiseless and noisy cases and establishes sharp restricted isometry conditions for sparse signal and low-rank matrix recovery. The analysis relies on a key technical tool which represents points in a polytope by convex combinations of sparse vectors. The technique is elementary while leads to sharp results. It is shown that, in compressed sensing, delta kA 0, delta kA < 1/3 + epsilon, deltak A + thetak,kA < 1 + epsilon, or deltatkA< √(t - 1) / t + epsilon are not sufficient to guarantee the exact recovery of all k-sparse signals for large k. Similar result also holds for matrix recovery. In addition, the conditions delta kA<1/3, deltak A+ thetak,kA<1, delta tkA < √(t - 1)/t and deltarM<1/3, delta rM+ thetar,rM<1, delta trM< √(t - 1)/ t are also shown to be sufficient respectively for stable recovery of approximately sparse signals and low-rank matrices in the noisy case. For the second part of the thesis, we introduce a rank-one projection model for low-rank matrix recovery and propose a constrained nuclear norm minimization method for stable recovery of low-rank matrices in the noisy case. The procedure is adaptive to the rank and robust against small perturbations. Both upper and lower bounds for the estimation accuracy under the Frobenius norm loss are obtained. The proposed estimator is shown to be rate-optimal under certain conditions. The

BCYCLIC: A parallel block tridiagonal matrix cyclic solver

Science.gov (United States)

Hirshman, S. P.; Perumalla, K. S.; Lynch, V. E.; Sanchez, R.

2010-09-01

A block tridiagonal matrix is factored with minimal fill-in using a cyclic reduction algorithm that is easily parallelized. Storage of the factored blocks allows the application of the inverse to multiple right-hand sides which may not be known at factorization time. Scalability with the number of block rows is achieved with cyclic reduction, while scalability with the block size is achieved using multithreaded routines (OpenMP, GotoBLAS) for block matrix manipulation. This dual scalability is a noteworthy feature of this new solver, as well as its ability to efficiently handle arbitrary (non-powers-of-2) block row and processor numbers. Comparison with a state-of-the art parallel sparse solver is presented. It is expected that this new solver will allow many physical applications to optimally use the parallel resources on current supercomputers. Example usage of the solver in magneto-hydrodynamic (MHD), three-dimensional equilibrium solvers for high-temperature fusion plasmas is cited.

Global Convergence of Schubert’s Method for Solving Sparse Nonlinear Equations

Directory of Open Access Journals (Sweden)

Huiping Cao

2014-01-01

Full Text Available Schubert’s method is an extension of Broyden’s method for solving sparse nonlinear equations, which can preserve the zero-nonzero structure defined by the sparse Jacobian matrix and can retain many good properties of Broyden’s method. In particular, Schubert’s method has been proved to be locally and q-superlinearly convergent. In this paper, we globalize Schubert’s method by using a nonmonotone line search. Under appropriate conditions, we show that the proposed algorithm converges globally and superlinearly. Some preliminary numerical experiments are presented, which demonstrate that our algorithm is effective for large-scale problems.

Sparse Channel Estimation Including the Impact of the Transceiver Filters with Application to OFDM

DEFF Research Database (Denmark)

Barbu, Oana-Elena; Pedersen, Niels Lovmand; Manchón, Carles Navarro

2014-01-01

Traditionally, the dictionary matrices used in sparse wireless channel estimation have been based on the discrete Fourier transform, following the assumption that the channel frequency response (CFR) can be approximated as a linear combination of a small number of multipath components, each one......) and receive (demodulation) filters. Hence, the assumption of the CFR being sparse in the canonical Fourier dictionary may no longer hold. In this work, we derive a signal model and subsequently a novel dictionary matrix for sparse estimation that account for the impact of transceiver filters. Numerical...... results obtained in an OFDM transmission scenario demonstrate the superior accuracy of a sparse estimator that uses our proposed dictionary rather than the classical Fourier dictionary, and its robustness against a mismatch in the assumed transmit filter characteristics....

Sparse modeling of spatial environmental variables associated with asthma.

Science.gov (United States)

Chang, Timothy S; Gangnon, Ronald E; David Page, C; Buckingham, William R; Tandias, Aman; Cowan, Kelly J; Tomasallo, Carrie D; Arndt, Brian G; Hanrahan, Lawrence P; Guilbert, Theresa W

2015-02-01

Geographically distributed environmental factors influence the burden of diseases such as asthma. Our objective was to identify sparse environmental variables associated with asthma diagnosis gathered from a large electronic health record (EHR) dataset while controlling for spatial variation. An EHR dataset from the University of Wisconsin's Family Medicine, Internal Medicine and Pediatrics Departments was obtained for 199,220 patients aged 5-50years over a three-year period. Each patient's home address was geocoded to one of 3456 geographic census block groups. Over one thousand block group variables were obtained from a commercial database. We developed a Sparse Spatial Environmental Analysis (SASEA). Using this method, the environmental variables were first dimensionally reduced with sparse principal component analysis. Logistic thin plate regression spline modeling was then used to identify block group variables associated with asthma from sparse principal components. The addresses of patients from the EHR dataset were distributed throughout the majority of Wisconsin's geography. Logistic thin plate regression spline modeling captured spatial variation of asthma. Four sparse principal components identified via model selection consisted of food at home, dog ownership, household size, and disposable income variables. In rural areas, dog ownership and renter occupied housing units from significant sparse principal components were associated with asthma. Our main contribution is the incorporation of sparsity in spatial modeling. SASEA sequentially added sparse principal components to Logistic thin plate regression spline modeling. This method allowed association of geographically distributed environmental factors with asthma using EHR and environmental datasets. SASEA can be applied to other diseases with environmental risk factors. Copyright © 2014 Elsevier Inc. All rights reserved.

Sparse Localization with a Mobile Beacon Based on LU Decomposition in Wireless Sensor Networks

Directory of Open Access Journals (Sweden)

Chunhui Zhao

2015-09-01

Full Text Available Node localization is the core in wireless sensor network. It can be solved by powerful beacons, which are equipped with global positioning system devices to know their location information. In this article, we present a novel sparse localization approach with a mobile beacon based on LU decomposition. Our scheme firstly translates node localization problem into a 1-sparse vector recovery problem by establishing sparse localization model. Then, LU decomposition pre-processing is adopted to solve the problem that measurement matrix does not meet the re¬stricted isometry property. Later, the 1-sparse vector can be exactly recovered by compressive sensing. Finally, as the 1-sparse vector is approximate sparse, weighted Cen¬troid scheme is introduced to accurately locate the node. Simulation and analysis show that our scheme has better localization performance and lower requirement for the mobile beacon than MAP+GC, MAP-M, and MAP-MN schemes. In addition, the obstacles and DOI have little effect on the novel scheme, and it has great localization performance under low SNR, thus, the scheme proposed is robust.

Z4-symmetric factorized S-matrix in two space-time dimensions

International Nuclear Information System (INIS)

Zamolodchikov, A.B.

1979-01-01

The factorized S-matrix with internal symmetry Z 4 is constructed in two space-time dimensions. The two-particle amplitudes are obtained by means of solving the factorization, unitarity and analyticity equations. The solution of factorization equations can be expressed in terms of elliptic functions. The S-matrix cotains the resonance poles naturally. The simple formal relation between the general factorized S-matrices and the Baxter-type lattice transfer matrices is found. In the sense of this relation the Z 4 -symmetric S-matrix corresponds to the Baxter transfer matrix itself. (orig.)

Shifted Non-negative Matrix Factorization

DEFF Research Database (Denmark)

Mørup, Morten; Madsen, Kristoffer Hougaard; Hansen, Lars Kai

2007-01-01

Non-negative matrix factorization (NMF) has become a widely used blind source separation technique due to its part based representation and ease of interpretability. We currently extend the NMF model to allow for delays between sources and sensors. This is a natural extension for spectrometry data...

Multi-view clustering via multi-manifold regularized non-negative matrix factorization.

Science.gov (United States)

Zong, Linlin; Zhang, Xianchao; Zhao, Long; Yu, Hong; Zhao, Qianli

2017-04-01

Non-negative matrix factorization based multi-view clustering algorithms have shown their competitiveness among different multi-view clustering algorithms. However, non-negative matrix factorization fails to preserve the locally geometrical structure of the data space. In this paper, we propose a multi-manifold regularized non-negative matrix factorization framework (MMNMF) which can preserve the locally geometrical structure of the manifolds for multi-view clustering. MMNMF incorporates consensus manifold and consensus coefficient matrix with multi-manifold regularization to preserve the locally geometrical structure of the multi-view data space. We use two methods to construct the consensus manifold and two methods to find the consensus coefficient matrix, which leads to four instances of the framework. Experimental results show that the proposed algorithms outperform existing non-negative matrix factorization based algorithms for multi-view clustering. Copyright © 2017 Elsevier Ltd. All rights reserved.

Semi-supervised sparse coding

KAUST Repository

Wang, Jim Jing-Yan; Gao, Xin

2014-01-01

Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a semi-supervised manner, where only a few training samples are labeled. By using the manifold structure spanned by the data set of both labeled and unlabeled samples and the constraints provided by the labels of the labeled samples, we learn the variable class labels for all the samples. Furthermore, to improve the discriminative ability of the learned sparse codes, we assume that the class labels could be predicted from the sparse codes directly using a linear classifier. By solving the codebook, sparse codes, class labels and classifier parameters simultaneously in a unified objective function, we develop a semi-supervised sparse coding algorithm. Experiments on two real-world pattern recognition problems demonstrate the advantage of the proposed methods over supervised sparse coding methods on partially labeled data sets.

Semi-supervised sparse coding

KAUST Repository

Wang, Jim Jing-Yan

2014-07-06

Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a semi-supervised manner, where only a few training samples are labeled. By using the manifold structure spanned by the data set of both labeled and unlabeled samples and the constraints provided by the labels of the labeled samples, we learn the variable class labels for all the samples. Furthermore, to improve the discriminative ability of the learned sparse codes, we assume that the class labels could be predicted from the sparse codes directly using a linear classifier. By solving the codebook, sparse codes, class labels and classifier parameters simultaneously in a unified objective function, we develop a semi-supervised sparse coding algorithm. Experiments on two real-world pattern recognition problems demonstrate the advantage of the proposed methods over supervised sparse coding methods on partially labeled data sets.

The Roles of Sparse Direct Methods in Large-scale Simulations

Energy Technology Data Exchange (ETDEWEB)

Li, Xiaoye S.; Gao, Weiguo; Husbands, Parry J.R.; Yang, Chao; Ng, Esmond G.

2005-06-27

Sparse systems of linear equations and eigen-equations arise at the heart of many large-scale, vital simulations in DOE. Examples include the Accelerator Science and Technology SciDAC (Omega3P code, electromagnetic problem), the Center for Extended Magnetohydrodynamic Modeling SciDAC(NIMROD and M3D-C1 codes, fusion plasma simulation). The Terascale Optimal PDE Simulations (TOPS)is providing high-performance sparse direct solvers, which have had significant impacts on these applications. Over the past several years, we have been working closely with the other SciDAC teams to solve their large, sparse matrix problems arising from discretization of the partial differential equations. Most of these systems are very ill-conditioned, resulting in extremely poor convergence deployed our direct methods techniques in these applications, which achieved significant scientific results as well as performance gains. These successes were made possible through the SciDAC model of computer scientists and application scientists working together to take full advantage of terascale computing systems and new algorithms research.

The Roles of Sparse Direct Methods in Large-scale Simulations

International Nuclear Information System (INIS)

Li, Xiaoye S.; Gao, Weiguo; Husbands, Parry J.R.; Yang, Chao; Ng, Esmond G.

2005-01-01

Sparse systems of linear equations and eigen-equations arise at the heart of many large-scale, vital simulations in DOE. Examples include the Accelerator Science and Technology SciDAC (Omega3P code, electromagnetic problem), the Center for Extended Magnetohydrodynamic Modeling SciDAC(NIMROD and M3D-C1 codes, fusion plasma simulation). The Terascale Optimal PDE Simulations (TOPS)is providing high-performance sparse direct solvers, which have had significant impacts on these applications. Over the past several years, we have been working closely with the other SciDAC teams to solve their large, sparse matrix problems arising from discretization of the partial differential equations. Most of these systems are very ill-conditioned, resulting in extremely poor convergence deployed our direct methods techniques in these applications, which achieved significant scientific results as well as performance gains. These successes were made possible through the SciDAC model of computer scientists and application scientists working together to take full advantage of terascale computing systems and new algorithms research

Sparse BLIP: BLind Iterative Parallel imaging reconstruction using compressed sensing.

Science.gov (United States)

She, Huajun; Chen, Rong-Rong; Liang, Dong; DiBella, Edward V R; Ying, Leslie

2014-02-01

To develop a sensitivity-based parallel imaging reconstruction method to reconstruct iteratively both the coil sensitivities and MR image simultaneously based on their prior information. Parallel magnetic resonance imaging reconstruction problem can be formulated as a multichannel sampling problem where solutions are sought analytically. However, the channel functions given by the coil sensitivities in parallel imaging are not known exactly and the estimation error usually leads to artifacts. In this study, we propose a new reconstruction algorithm, termed Sparse BLind Iterative Parallel, for blind iterative parallel imaging reconstruction using compressed sensing. The proposed algorithm reconstructs both the sensitivity functions and the image simultaneously from undersampled data. It enforces the sparseness constraint in the image as done in compressed sensing, but is different from compressed sensing in that the sensing matrix is unknown and additional constraint is enforced on the sensitivities as well. Both phantom and in vivo imaging experiments were carried out with retrospective undersampling to evaluate the performance of the proposed method. Experiments show improvement in Sparse BLind Iterative Parallel reconstruction when compared with Sparse SENSE, JSENSE, IRGN-TV, and L1-SPIRiT reconstructions with the same number of measurements. The proposed Sparse BLind Iterative Parallel algorithm reduces the reconstruction errors when compared to the state-of-the-art parallel imaging methods. Copyright © 2013 Wiley Periodicals, Inc.

The application of sparse estimation of covariance matrix to quadratic discriminant analysis.

Science.gov (United States)

Sun, Jiehuan; Zhao, Hongyu

2015-02-18

Although Linear Discriminant Analysis (LDA) is commonly used for classification, it may not be directly applied in genomics studies due to the large p, small n problem in these studies. Different versions of sparse LDA have been proposed to address this significant challenge. One implicit assumption of various LDA-based methods is that the covariance matrices are the same across different classes. However, rewiring of genetic networks (therefore different covariance matrices) across different diseases has been observed in many genomics studies, which suggests that LDA and its variations may be suboptimal for disease classifications. However, it is not clear whether considering differing genetic networks across diseases can improve classification in genomics studies. We propose a sparse version of Quadratic Discriminant Analysis (SQDA) to explicitly consider the differences of the genetic networks across diseases. Both simulation and real data analysis are performed to compare the performance of SQDA with six commonly used classification methods. SQDA provides more accurate classification results than other methods for both simulated and real data. Our method should prove useful for classification in genomics studies and other research settings, where covariances differ among classes.

In Defense of Sparse Tracking: Circulant Sparse Tracker

KAUST Repository

Zhang, Tianzhu; Bibi, Adel Aamer; Ghanem, Bernard

2016-01-01

Sparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework. However, most sparse representation based trackers have high computational cost, less than promising tracking performance, and limited feature representation. To deal with the above issues, we propose a novel circulant sparse tracker (CST), which exploits circulant target templates. Because of the circulant structure property, CST has the following advantages: (1) It can refine and reduce particles using circular shifts of target templates. (2) The optimization can be efficiently solved entirely in the Fourier domain. (3) High dimensional features can be embedded into CST to significantly improve tracking performance without sacrificing much computation time. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that CST performs better than all other sparse trackers and favorably against state-of-the-art methods.

In Defense of Sparse Tracking: Circulant Sparse Tracker

KAUST Repository

Zhang, Tianzhu

2016-12-13

Sparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework. However, most sparse representation based trackers have high computational cost, less than promising tracking performance, and limited feature representation. To deal with the above issues, we propose a novel circulant sparse tracker (CST), which exploits circulant target templates. Because of the circulant structure property, CST has the following advantages: (1) It can refine and reduce particles using circular shifts of target templates. (2) The optimization can be efficiently solved entirely in the Fourier domain. (3) High dimensional features can be embedded into CST to significantly improve tracking performance without sacrificing much computation time. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that CST performs better than all other sparse trackers and favorably against state-of-the-art methods.

Max–min distance nonnegative matrix factorization

KAUST Repository

Wang, Jim Jing-Yan; Gao, Xin

2014-01-01

Nonnegative Matrix Factorization (NMF) has been a popular representation method for pattern classification problems. It tries to decompose a nonnegative matrix of data samples as the product of a nonnegative basis matrix and a nonnegative coefficient matrix. The columns of the coefficient matrix can be used as new representations of these data samples. However, traditional NMF methods ignore class labels of the data samples. In this paper, we propose a novel supervised NMF algorithm to improve the discriminative ability of the new representation by using the class labels. Using the class labels, we separate all the data sample pairs into within-class pairs and between-class pairs. To improve the discriminative ability of the new NMF representations, we propose to minimize the maximum distance of the within-class pairs in the new NMF space, and meanwhile to maximize the minimum distance of the between-class pairs. With this criterion, we construct an objective function and optimize it with regard to basis and coefficient matrices, and slack variables alternatively, resulting in an iterative algorithm. The proposed algorithm is evaluated on three pattern classification problems and experiment results show that it outperforms the state-of-the-art supervised NMF methods.

Max–min distance nonnegative matrix factorization

KAUST Repository

Wang, Jim Jing-Yan

2014-10-26

Nonnegative Matrix Factorization (NMF) has been a popular representation method for pattern classification problems. It tries to decompose a nonnegative matrix of data samples as the product of a nonnegative basis matrix and a nonnegative coefficient matrix. The columns of the coefficient matrix can be used as new representations of these data samples. However, traditional NMF methods ignore class labels of the data samples. In this paper, we propose a novel supervised NMF algorithm to improve the discriminative ability of the new representation by using the class labels. Using the class labels, we separate all the data sample pairs into within-class pairs and between-class pairs. To improve the discriminative ability of the new NMF representations, we propose to minimize the maximum distance of the within-class pairs in the new NMF space, and meanwhile to maximize the minimum distance of the between-class pairs. With this criterion, we construct an objective function and optimize it with regard to basis and coefficient matrices, and slack variables alternatively, resulting in an iterative algorithm. The proposed algorithm is evaluated on three pattern classification problems and experiment results show that it outperforms the state-of-the-art supervised NMF methods.

Low-rank sparse learning for robust visual tracking

KAUST Repository

Zhang, Tianzhu

2012-01-01

In this paper, we propose a new particle-filter based tracking algorithm that exploits the relationship between particles (candidate targets). By representing particles as sparse linear combinations of dictionary templates, this algorithm capitalizes on the inherent low-rank structure of particle representations that are learned jointly. As such, it casts the tracking problem as a low-rank matrix learning problem. This low-rank sparse tracker (LRST) has a number of attractive properties. (1) Since LRST adaptively updates dictionary templates, it can handle significant changes in appearance due to variations in illumination, pose, scale, etc. (2) The linear representation in LRST explicitly incorporates background templates in the dictionary and a sparse error term, which enables LRST to address the tracking drift problem and to be robust against occlusion respectively. (3) LRST is computationally attractive, since the low-rank learning problem can be efficiently solved as a sequence of closed form update operations, which yield a time complexity that is linear in the number of particles and the template size. We evaluate the performance of LRST by applying it to a set of challenging video sequences and comparing it to 6 popular tracking methods. Our experiments show that by representing particles jointly, LRST not only outperforms the state-of-the-art in tracking accuracy but also significantly improves the time complexity of methods that use a similar sparse linear representation model for particles [1]. © 2012 Springer-Verlag.

Partitioning sparse rectangular matrices for parallel processing

Energy Technology Data Exchange (ETDEWEB)

Kolda, T.G.

1998-05-01

The authors are interested in partitioning sparse rectangular matrices for parallel processing. The partitioning problem has been well-studied in the square symmetric case, but the rectangular problem has received very little attention. They will formalize the rectangular matrix partitioning problem and discuss several methods for solving it. They will extend the spectral partitioning method for symmetric matrices to the rectangular case and compare this method to three new methods -- the alternating partitioning method and two hybrid methods. The hybrid methods will be shown to be best.

Matrix factorizations and homological mirror symmetry on the torus

International Nuclear Information System (INIS)

Knapp, Johanna; Omer, Harun

2007-01-01

We consider matrix factorizations and homological mirror symmetry on the torus T 2 using a Landau-Ginzburg description. We identify the basic matrix factorizations of the Landau-Ginzburg superpotential and compute the full spectrum taking into account the explicit dependence on bulk and boundary moduli. We verify homological mirror symmetry by comparing three-point functions in the A-model and the B-model

NoGOA: predicting noisy GO annotations using evidences and sparse representation.

Science.gov (United States)

Yu, Guoxian; Lu, Chang; Wang, Jun

2017-07-21

Gene Ontology (GO) is a community effort to represent functional features of gene products. GO annotations (GOA) provide functional associations between GO terms and gene products. Due to resources limitation, only a small portion of annotations are manually checked by curators, and the others are electronically inferred. Although quality control techniques have been applied to ensure the quality of annotations, the community consistently report that there are still considerable noisy (or incorrect) annotations. Given the wide application of annotations, however, how to identify noisy annotations is an important but yet seldom studied open problem. We introduce a novel approach called NoGOA to predict noisy annotations. NoGOA applies sparse representation on the gene-term association matrix to reduce the impact of noisy annotations, and takes advantage of sparse representation coefficients to measure the semantic similarity between genes. Secondly, it preliminarily predicts noisy annotations of a gene based on aggregated votes from semantic neighborhood genes of that gene. Next, NoGOA estimates the ratio of noisy annotations for each evidence code based on direct annotations in GOA files archived on different periods, and then weights entries of the association matrix via estimated ratios and propagates weights to ancestors of direct annotations using GO hierarchy. Finally, it integrates evidence-weighted association matrix and aggregated votes to predict noisy annotations. Experiments on archived GOA files of six model species (H. sapiens, A. thaliana, S. cerevisiae, G. gallus, B. Taurus and M. musculus) demonstrate that NoGOA achieves significantly better results than other related methods and removing noisy annotations improves the performance of gene function prediction. The comparative study justifies the effectiveness of integrating evidence codes with sparse representation for predicting noisy GO annotations. Codes and datasets are available at http://mlda.swu.edu.cn/codes.php?name=NoGOA .

Matrix factorization on a hypercube multiprocessor

International Nuclear Information System (INIS)

Geist, G.A.; Heath, M.T.

1985-08-01

This paper is concerned with parallel algorithms for matrix factorization on distributed-memory, message-passing multiprocessors, with special emphasis on the hypercube. Both Cholesky factorization of symmetric positive definite matrices and LU factorization of nonsymmetric matrices using partial pivoting are considered. The use of the resulting triangular factors to solve systems of linear equations by forward and back substitutions is also considered. Efficiencies of various parallel computational approaches are compared in terms of empirical results obtained on an Intel iPSC hypercube. 19 refs., 6 figs., 2 tabs

Signal Sampling for Efficient Sparse Representation of Resting State FMRI Data

Science.gov (United States)

Ge, Bao; Makkie, Milad; Wang, Jin; Zhao, Shijie; Jiang, Xi; Li, Xiang; Lv, Jinglei; Zhang, Shu; Zhang, Wei; Han, Junwei; Guo, Lei; Liu, Tianming

2015-01-01

As the size of brain imaging data such as fMRI grows explosively, it provides us with unprecedented and abundant information about the brain. How to reduce the size of fMRI data but not lose much information becomes a more and more pressing issue. Recent literature studies tried to deal with it by dictionary learning and sparse representation methods, however, their computation complexities are still high, which hampers the wider application of sparse representation method to large scale fMRI datasets. To effectively address this problem, this work proposes to represent resting state fMRI (rs-fMRI) signals of a whole brain via a statistical sampling based sparse representation. First we sampled the whole brain’s signals via different sampling methods, then the sampled signals were aggregate into an input data matrix to learn a dictionary, finally this dictionary was used to sparsely represent the whole brain’s signals and identify the resting state networks. Comparative experiments demonstrate that the proposed signal sampling framework can speed-up by ten times in reconstructing concurrent brain networks without losing much information. The experiments on the 1000 Functional Connectomes Project further demonstrate its effectiveness and superiority. PMID:26646924

The application of sparse estimation of covariance matrix to quadratic discriminant analysis

OpenAIRE

Sun, Jiehuan; Zhao, Hongyu

2015-01-01

Background Although Linear Discriminant Analysis (LDA) is commonly used for classification, it may not be directly applied in genomics studies due to the large p, small n problem in these studies. Different versions of sparse LDA have been proposed to address this significant challenge. One implicit assumption of various LDA-based methods is that the covariance matrices are the same across different classes. However, rewiring of genetic networks (therefore different covariance matrices) acros...

Single-channel source separation using non-negative matrix factorization

DEFF Research Database (Denmark)

Schmidt, Mikkel Nørgaard

-determined and its solution relies on making appropriate assumptions concerning the sources. This dissertation is concerned with model-based probabilistic single-channel source separation based on non-negative matrix factorization, and consists of two parts: i) three introductory chapters and ii) five published...... papers. The first part introduces the single-channel source separation problem as well as non-negative matrix factorization and provides a comprehensive review of existing approaches, applications, and practical algorithms. This serves to provide context for the second part, the published papers......, in which a number of methods for single-channel source separation based on non-negative matrix factorization are presented. In the papers, the methods are applied to separating audio signals such as speech and musical instruments and separating different types of tissue in chemical shift imaging....

Contribution of non-negative matrix factorization to the classification of remote sensing images

Science.gov (United States)

Karoui, M. S.; Deville, Y.; Hosseini, S.; Ouamri, A.; Ducrot, D.

2008-10-01

Remote sensing has become an unavoidable tool for better managing our environment, generally by realizing maps of land cover using classification techniques. The classification process requires some pre-processing, especially for data size reduction. The most usual technique is Principal Component Analysis. Another approach consists in regarding each pixel of the multispectral image as a mixture of pure elements contained in the observed area. Using Blind Source Separation (BSS) methods, one can hope to unmix each pixel and to perform the recognition of the classes constituting the observed scene. Our contribution consists in using Non-negative Matrix Factorization (NMF) combined with sparse coding as a solution to BSS, in order to generate new images (which are at least partly separated images) using HRV SPOT images from Oran area, Algeria). These images are then used as inputs of a supervised classifier integrating textural information. The results of classifications of these "separated" images show a clear improvement (correct pixel classification rate improved by more than 20%) compared to classification of initial (i.e. non separated) images. These results show the contribution of NMF as an attractive pre-processing for classification of multispectral remote sensing imagery.

Mini-lecture course: Introduction into hierarchical matrix technique

KAUST Repository

Litvinenko, Alexander

2017-12-14

The H-matrix format has a log-linear computational cost and storage O(kn log n), where the rank k is a small integer and n is the number of locations (mesh points). The H-matrix technique allows us to work with general class of matrices (not only structured or Toeplits or sparse). H-matrices can keep the H-matrix data format during linear algebra operations (inverse, update, Schur complement).

Covariance matrix estimation for stationary time series

OpenAIRE

Xiao, Han; Wu, Wei Biao

2011-01-01

We obtain a sharp convergence rate for banded covariance matrix estimates of stationary processes. A precise order of magnitude is derived for spectral radius of sample covariance matrices. We also consider a thresholded covariance matrix estimator that can better characterize sparsity if the true covariance matrix is sparse. As our main tool, we implement Toeplitz [Math. Ann. 70 (1911) 351–376] idea and relate eigenvalues of covariance matrices to the spectral densities or Fourier transforms...

Normalization Of Thermal-Radiation Form-Factor Matrix

Science.gov (United States)

Tsuyuki, Glenn T.

1994-01-01

Report describes algorithm that adjusts form-factor matrix in TRASYS computer program, which calculates intraspacecraft radiative interchange among various surfaces and environmental heat loading from sources such as sun.

Superresolution radar imaging based on fast inverse-free sparse Bayesian learning for multiple measurement vectors

Science.gov (United States)

He, Xingyu; Tong, Ningning; Hu, Xiaowei

2018-01-01

Compressive sensing has been successfully applied to inverse synthetic aperture radar (ISAR) imaging of moving targets. By exploiting the block sparse structure of the target image, sparse solution for multiple measurement vectors (MMV) can be applied in ISAR imaging and a substantial performance improvement can be achieved. As an effective sparse recovery method, sparse Bayesian learning (SBL) for MMV involves a matrix inverse at each iteration. Its associated computational complexity grows significantly with the problem size. To address this problem, we develop a fast inverse-free (IF) SBL method for MMV. A relaxed evidence lower bound (ELBO), which is computationally more amiable than the traditional ELBO used by SBL, is obtained by invoking fundamental property for smooth functions. A variational expectation-maximization scheme is then employed to maximize the relaxed ELBO, and a computationally efficient IF-MSBL algorithm is proposed. Numerical results based on simulated and real data show that the proposed method can reconstruct row sparse signal accurately and obtain clear superresolution ISAR images. Moreover, the running time and computational complexity are reduced to a great extent compared with traditional SBL methods.

Matrix factorizations, minimal models and Massey products

International Nuclear Information System (INIS)

Knapp, Johanna; Omer, Harun

2006-01-01

We present a method to compute the full non-linear deformations of matrix factorizations for ADE minimal models. This method is based on the calculation of higher products in the cohomology, called Massey products. The algorithm yields a polynomial ring whose vanishing relations encode the obstructions of the deformations of the D-branes characterized by these matrix factorizations. This coincides with the critical locus of the effective superpotential which can be computed by integrating these relations. Our results for the effective superpotential are in agreement with those obtained from solving the A-infinity relations. We point out a relation to the superpotentials of Kazama-Suzuki models. We will illustrate our findings by various examples, putting emphasis on the E 6 minimal model

Structural Sparse Tracking

KAUST Repository

Zhang, Tianzhu

2015-06-01

Sparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates. However, most sparse representation based trackers only consider holistic or local representations and do not make full use of the intrinsic structure among and inside target candidates, thereby making the representation less effective when similar objects appear or under occlusion. In this paper, we propose a novel Structural Sparse Tracking (SST) algorithm, which not only exploits the intrinsic relationship among target candidates and their local patches to learn their sparse representations jointly, but also preserves the spatial layout structure among the local patches inside each target candidate. We show that our SST algorithm accommodates most existing sparse trackers with the respective merits. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SST algorithm performs favorably against several state-of-the-art methods.

Multiple graph regularized nonnegative matrix factorization

KAUST Repository

Wang, Jim Jing-Yan

2013-10-01

Non-negative matrix factorization (NMF) has been widely used as a data representation method based on components. To overcome the disadvantage of NMF in failing to consider the manifold structure of a data set, graph regularized NMF (GrNMF) has been proposed by Cai et al. by constructing an affinity graph and searching for a matrix factorization that respects graph structure. Selecting a graph model and its corresponding parameters is critical for this strategy. This process is usually carried out by cross-validation or discrete grid search, which are time consuming and prone to overfitting. In this paper, we propose a GrNMF, called MultiGrNMF, in which the intrinsic manifold is approximated by a linear combination of several graphs with different models and parameters inspired by ensemble manifold regularization. Factorization metrics and linear combination coefficients of graphs are determined simultaneously within a unified object function. They are alternately optimized in an iterative algorithm, thus resulting in a novel data representation algorithm. Extensive experiments on a protein subcellular localization task and an Alzheimer\\'s disease diagnosis task demonstrate the effectiveness of the proposed algorithm. © 2013 Elsevier Ltd. All rights reserved.

ℓ1/2-norm regularized nonnegative low-rank and sparse affinity graph for remote sensing image segmentation

Science.gov (United States)

Tian, Shu; Zhang, Ye; Yan, Yiming; Su, Nan

2016-10-01

Segmentation of real-world remote sensing images is a challenge due to the complex texture information with high heterogeneity. Thus, graph-based image segmentation methods have been attracting great attention in the field of remote sensing. However, most of the traditional graph-based approaches fail to capture the intrinsic structure of the feature space and are sensitive to noises. A ℓ-norm regularization-based graph segmentation method is proposed to segment remote sensing images. First, we use the occlusion of the random texture model (ORTM) to extract the local histogram features. Then, a ℓ-norm regularized low-rank and sparse representation (LNNLRS) is implemented to construct a ℓ-regularized nonnegative low-rank and sparse graph (LNNLRS-graph), by the union of feature subspaces. Moreover, the LNNLRS-graph has a high ability to discriminate the manifold intrinsic structure of highly homogeneous texture information. Meanwhile, the LNNLRS representation takes advantage of the low-rank and sparse characteristics to remove the noises and corrupted data. Last, we introduce the LNNLRS-graph into the graph regularization nonnegative matrix factorization to enhance the segmentation accuracy. The experimental results using remote sensing images show that when compared to five state-of-the-art image segmentation methods, the proposed method achieves more accurate segmentation results.

Estimating Depolarization with the Jones Matrix Quality Factor

Science.gov (United States)

Hilfiker, James N.; Hale, Jeffrey S.; Herzinger, Craig M.; Tiwald, Tom; Hong, Nina; Schöche, Stefan; Arwin, Hans

2017-11-01

Mueller matrix (MM) measurements offer the ability to quantify the depolarization capability of a sample. Depolarization can be estimated using terms such as the depolarization index or the average degree of polarization. However, these calculations require measurement of the complete MM. We propose an alternate depolarization metric, termed the Jones matrix quality factor, QJM, which does not require the complete MM. This metric provides a measure of how close, in a least-squares sense, a Jones matrix can be found to the measured Mueller matrix. We demonstrate and compare the use of QJM to other traditional calculations of depolarization for both isotropic and anisotropic depolarizing samples; including non-uniform coatings, anisotropic crystal substrates, and beetle cuticles that exhibit both depolarization and circular diattenuation.

Speech Denoising in White Noise Based on Signal Subspace Low-rank Plus Sparse Decomposition

Directory of Open Access Journals (Sweden)

yuan Shuai

2017-01-01

Full Text Available In this paper, a new subspace speech enhancement method using low-rank and sparse decomposition is presented. In the proposed method, we firstly structure the corrupted data as a Toeplitz matrix and estimate its effective rank for the underlying human speech signal. Then the low-rank and sparse decomposition is performed with the guidance of speech rank value to remove the noise. Extensive experiments have been carried out in white Gaussian noise condition, and experimental results show the proposed method performs better than conventional speech enhancement methods, in terms of yielding less residual noise and lower speech distortion.

Mini-lecture course: Introduction into hierarchical matrix technique

KAUST Repository

Litvinenko, Alexander

2017-01-01

allows us to work with general class of matrices (not only structured or Toeplits or sparse). H-matrices can keep the H-matrix data format during linear algebra operations (inverse, update, Schur complement).

Sparse inverse covariance estimation with the graphical lasso.

Science.gov (United States)

Friedman, Jerome; Hastie, Trevor; Tibshirani, Robert

2008-07-01

We consider the problem of estimating sparse graphs by a lasso penalty applied to the inverse covariance matrix. Using a coordinate descent procedure for the lasso, we develop a simple algorithm--the graphical lasso--that is remarkably fast: It solves a 1000-node problem ( approximately 500,000 parameters) in at most a minute and is 30-4000 times faster than competing methods. It also provides a conceptual link between the exact problem and the approximation suggested by Meinshausen and Bühlmann (2006). We illustrate the method on some cell-signaling data from proteomics.

PARTRACK - A particle tracking algorithm for transport and dispersion of solutes in a sparsely fractured rock

International Nuclear Information System (INIS)

Svensson, Urban

2001-04-01

A particle tracking algorithm, PARTRACK, that simulates transport and dispersion in a sparsely fractured rock is described. The main novel feature of the algorithm is the introduction of multiple particle states. It is demonstrated that the introduction of this feature allows for the simultaneous simulation of Taylor dispersion, sorption and matrix diffusion. A number of test cases are used to verify and demonstrate the features of PARTRACK. It is shown that PARTRACK can simulate the following processes, believed to be important for the problem addressed: the split up of a tracer cloud at a fracture intersection, channeling in a fracture plane, Taylor dispersion and matrix diffusion and sorption. From the results of the test cases, it is concluded that PARTRACK is an adequate framework for simulation of transport and dispersion of a solute in a sparsely fractured rock

Generic, network schema agnostic sparse tensor factorization for single-pass clustering of heterogeneous information networks.

Science.gov (United States)

Wu, Jibing; Meng, Qinggang; Deng, Su; Huang, Hongbin; Wu, Yahui; Badii, Atta

2017-01-01

Heterogeneous information networks (e.g. bibliographic networks and social media networks) that consist of multiple interconnected objects are ubiquitous. Clustering analysis is an effective method to understand the semantic information and interpretable structure of the heterogeneous information networks, and it has attracted the attention of many researchers in recent years. However, most studies assume that heterogeneous information networks usually follow some simple schemas, such as bi-typed networks or star network schema, and they can only cluster one type of object in the network each time. In this paper, a novel clustering framework is proposed based on sparse tensor factorization for heterogeneous information networks, which can cluster multiple types of objects simultaneously in a single pass without any network schema information. The types of objects and the relations between them in the heterogeneous information networks are modeled as a sparse tensor. The clustering issue is modeled as an optimization problem, which is similar to the well-known Tucker decomposition. Then, an Alternating Least Squares (ALS) algorithm and a feasible initialization method are proposed to solve the optimization problem. Based on the tensor factorization, we simultaneously partition different types of objects into different clusters. The experimental results on both synthetic and real-world datasets have demonstrated that our proposed clustering framework, STFClus, can model heterogeneous information networks efficiently and can outperform state-of-the-art clustering algorithms as a generally applicable single-pass clustering method for heterogeneous network which is network schema agnostic.

Iterative solution of general sparse linear systems on clusters of workstations

Energy Technology Data Exchange (ETDEWEB)

Lo, Gen-Ching; Saad, Y. [Univ. of Minnesota, Minneapolis, MN (United States)

1996-12-31

Solving sparse irregularly structured linear systems on parallel platforms poses several challenges. First, sparsity makes it difficult to exploit data locality, whether in a distributed or shared memory environment. A second, perhaps more serious challenge, is to find efficient ways to precondition the system. Preconditioning techniques which have a large degree of parallelism, such as multicolor SSOR, often have a slower rate of convergence than their sequential counterparts. Finally, a number of other computational kernels such as inner products could ruin any gains gained from parallel speed-ups, and this is especially true on workstation clusters where start-up times may be high. In this paper we discuss these issues and report on our experience with PSPARSLIB, an on-going project for building a library of parallel iterative sparse matrix solvers.

Extracellular matrix organization modulates fibroblast growth and growth factor responsiveness.

Science.gov (United States)

Nakagawa, S; Pawelek, P; Grinnell, F

1989-06-01

To learn more about the relationship between extracellular matrix organization, cell shape, and cell growth control, we studied DNA synthesis by fibroblasts in collagen gels that were either attached to culture dishes or floating in culture medium during gel contraction. After 4 days of contraction, the collagen density (initially 1.5 mg/ml) reached 22 mg/ml in attached gels and 55 mg/ml in floating gels. After contraction, attached collagen gels were well organized; collagen fibrils were aligned in the plane of cell spreading; and fibroblasts had an elongated, bipolar morphology. Floating collagen gels, however, were unorganized; collagen fibrils were arranged randomly; and fibroblasts had a stellate morphology. DNA synthesis by fibroblasts in contracted collagen gels was suppressed if the gels were floating in medium but not if the gels were attached, and inhibition was independent of the extent of gel contraction. Therefore, growth of fibroblasts in contracted collagen gels could be regulated by differences in extracellular matrix organization and cell shape independently of extracellular matrix density. We also compared the responses of fibroblasts in contracted collagen gels and monolayer culture to peptide growth factors including fibroblast growth factor, platelet-derived growth factor, transforming growth factor-beta, and interleukin 1. Cells in floating collagen gels were generally unresponsive to any of the growth factors. Cells in attached collagen gels and monolayer culture were affected similarly by fibroblast growth factor but not by the others. Our results indicate that extracellular matrix organization influenced not only cell growth, but also fibroblast responsiveness to peptide growth factors.

A hierarchical model for ordinal matrix factorization

DEFF Research Database (Denmark)

Paquet, Ulrich; Thomson, Blaise; Winther, Ole

2012-01-01

This paper proposes a hierarchical probabilistic model for ordinal matrix factorization. Unlike previous approaches, we model the ordinal nature of the data and take a principled approach to incorporating priors for the hidden variables. Two algorithms are presented for inference, one based...

TRASYS form factor matrix normalization

Science.gov (United States)

Tsuyuki, Glenn T.

1992-01-01

A method has been developed for adjusting a TRASYS enclosure form factor matrix to unity. This approach is not limited to closed geometries, and in fact, it is primarily intended for use with open geometries. The purpose of this approach is to prevent optimistic form factors to space. In this method, nodal form factor sums are calculated within 0.05 of unity using TRASYS, although deviations as large as 0.10 may be acceptable, and then, a process is employed to distribute the difference amongst the nodes. A specific example has been analyzed with this method, and a comparison was performed with a standard approach for calculating radiation conductors. In this comparison, hot and cold case temperatures were determined. Exterior nodes exhibited temperature differences as large as 7 C and 3 C for the hot and cold cases, respectively when compared with the standard approach, while interior nodes demonstrated temperature differences from 0 C to 5 C. These results indicate that temperature predictions can be artificially biased if the form factor computation error is lumped into the individual form factors to space.

Followee recommendation in microblog using matrix factorization model with structural regularization.

Science.gov (United States)

Yu, Yan; Qiu, Robin G

2014-01-01

Microblog that provides us a new communication and information sharing platform has been growing exponentially since it emerged just a few years ago. To microblog users, recommending followees who can serve as high quality information sources is a competitive service. To address this problem, in this paper we propose a matrix factorization model with structural regularization to improve the accuracy of followee recommendation in microblog. More specifically, we adapt the matrix factorization model in traditional item recommender systems to followee recommendation in microblog and use structural regularization to exploit structure information of social network to constrain matrix factorization model. The experimental analysis on a real-world dataset shows that our proposed model is promising.

Proceedings of the third "international Traveling Workshop on Interactions between Sparse models and Technology" (iTWIST'16)

DEFF Research Database (Denmark)

2016-01-01

The third edition of the "international - Traveling Workshop on Interactions between Sparse models and Technology" (iTWIST) took place in Aalborg, the 4th largest city in Denmark situated beautifully in the northern part of the country, from the 24th to 26th of August 2016. The workshop venue...... learning; Optimization for sparse modelling; Information theory, geometry and randomness; Sparsity? What's next? (Discrete-valued signals; Union of low-dimensional spaces, Cosparsity, mixed/group norm, model-based, low-complexity models, ...); Matrix/manifold sensing/processing (graph, low...

SAR Target Recognition via Local Sparse Representation of Multi-Manifold Regularized Low-Rank Approximation

Directory of Open Access Journals (Sweden)

Meiting Yu

2018-02-01

Full Text Available The extraction of a valuable set of features and the design of a discriminative classifier are crucial for target recognition in SAR image. Although various features and classifiers have been proposed over the years, target recognition under extended operating conditions (EOCs is still a challenging problem, e.g., target with configuration variation, different capture orientations, and articulation. To address these problems, this paper presents a new strategy for target recognition. We first propose a low-dimensional representation model via incorporating multi-manifold regularization term into the low-rank matrix factorization framework. Two rules, pairwise similarity and local linearity, are employed for constructing multiple manifold regularization. By alternately optimizing the matrix factorization and manifold selection, the feature representation model can not only acquire the optimal low-rank approximation of original samples, but also capture the intrinsic manifold structure information. Then, to take full advantage of the local structure property of features and further improve the discriminative ability, local sparse representation is proposed for classification. Finally, extensive experiments on moving and stationary target acquisition and recognition (MSTAR database demonstrate the effectiveness of the proposed strategy, including target recognition under EOCs, as well as the capability of small training size.

Comparison of pressure transient response in intensely and sparsely fractured reservoirs

Energy Technology Data Exchange (ETDEWEB)

Johns, R.T.

1989-04-01

A comprehensive analytical model is presented to study the pressure transient behavior of a naturally fractured reservoir with a continuous matrix block size distribution. Geologically realistic probability density functions of matrix block size are used to represent reservoirs of varying fracture intensity and uniformity. Transient interporosity flow is assumed and interporosity skin is incorporated. Drawdown and interference pressure transient tests are investigated. The results show distinctions in the pressure response from intensely and sparsely fractured reservoirs in the absence of interporosity skin. Also, uniformly and nonuniformly fractured reservoirs exhibit distinct responses, irrespective of the degree of fracture intensity. The pressure response in a nonuniformly fractured reservoir with large block size variability, approaches a nonfractured (homogeneous) reservoir response. Type curves are developed to estimate matrix block size variability and the degree of fracture intensity from drawdown and interference well tests.

SAMBA: Sparse Approximation of Moment-Based Arbitrary Polynomial Chaos

Energy Technology Data Exchange (ETDEWEB)

Ahlfeld, R., E-mail: r.ahlfeld14@imperial.ac.uk; Belkouchi, B.; Montomoli, F.

2016-09-01

A new arbitrary Polynomial Chaos (aPC) method is presented for moderately high-dimensional problems characterised by limited input data availability. The proposed methodology improves the algorithm of aPC and extends the method, that was previously only introduced as tensor product expansion, to moderately high-dimensional stochastic problems. The fundamental idea of aPC is to use the statistical moments of the input random variables to develop the polynomial chaos expansion. This approach provides the possibility to propagate continuous or discrete probability density functions and also histograms (data sets) as long as their moments exist, are finite and the determinant of the moment matrix is strictly positive. For cases with limited data availability, this approach avoids bias and fitting errors caused by wrong assumptions. In this work, an alternative way to calculate the aPC is suggested, which provides the optimal polynomials, Gaussian quadrature collocation points and weights from the moments using only a handful of matrix operations on the Hankel matrix of moments. It can therefore be implemented without requiring prior knowledge about statistical data analysis or a detailed understanding of the mathematics of polynomial chaos expansions. The extension to more input variables suggested in this work, is an anisotropic and adaptive version of Smolyak's algorithm that is solely based on the moments of the input probability distributions. It is referred to as SAMBA (PC), which is short for Sparse Approximation of Moment-Based Arbitrary Polynomial Chaos. It is illustrated that for moderately high-dimensional problems (up to 20 different input variables or histograms) SAMBA can significantly simplify the calculation of sparse Gaussian quadrature rules. SAMBA's efficiency for multivariate functions with regard to data availability is further demonstrated by analysing higher order convergence and accuracy for a set of nonlinear test functions with 2, 5

SAMBA: Sparse Approximation of Moment-Based Arbitrary Polynomial Chaos

International Nuclear Information System (INIS)

Ahlfeld, R.; Belkouchi, B.; Montomoli, F.

2016-01-01

A new arbitrary Polynomial Chaos (aPC) method is presented for moderately high-dimensional problems characterised by limited input data availability. The proposed methodology improves the algorithm of aPC and extends the method, that was previously only introduced as tensor product expansion, to moderately high-dimensional stochastic problems. The fundamental idea of aPC is to use the statistical moments of the input random variables to develop the polynomial chaos expansion. This approach provides the possibility to propagate continuous or discrete probability density functions and also histograms (data sets) as long as their moments exist, are finite and the determinant of the moment matrix is strictly positive. For cases with limited data availability, this approach avoids bias and fitting errors caused by wrong assumptions. In this work, an alternative way to calculate the aPC is suggested, which provides the optimal polynomials, Gaussian quadrature collocation points and weights from the moments using only a handful of matrix operations on the Hankel matrix of moments. It can therefore be implemented without requiring prior knowledge about statistical data analysis or a detailed understanding of the mathematics of polynomial chaos expansions. The extension to more input variables suggested in this work, is an anisotropic and adaptive version of Smolyak's algorithm that is solely based on the moments of the input probability distributions. It is referred to as SAMBA (PC), which is short for Sparse Approximation of Moment-Based Arbitrary Polynomial Chaos. It is illustrated that for moderately high-dimensional problems (up to 20 different input variables or histograms) SAMBA can significantly simplify the calculation of sparse Gaussian quadrature rules. SAMBA's efficiency for multivariate functions with regard to data availability is further demonstrated by analysing higher order convergence and accuracy for a set of nonlinear test functions with 2, 5 and 10

Diffusion Indexes with Sparse Loadings

DEFF Research Database (Denmark)

Kristensen, Johannes Tang

The use of large-dimensional factor models in forecasting has received much attention in the literature with the consensus being that improvements on forecasts can be achieved when comparing with standard models. However, recent contributions in the literature have demonstrated that care needs...... to the problem by using the LASSO as a variable selection method to choose between the possible variables and thus obtain sparse loadings from which factors or diffusion indexes can be formed. This allows us to build a more parsimonious factor model which is better suited for forecasting compared...... it to be an important alternative to PC....

Wiener-Hopf factorization of piecewise meromorphic matrix-valued functions

International Nuclear Information System (INIS)

Adukov, Victor M

2009-01-01

Let D + be a multiply connected domain bounded by a contour Γ, let D - be the complement of D + union Γ in C-bar=C union {∞}, and a(t) be a continuous invertible matrix-valued function on Γ which can be meromorphically extended into the open disconnected set D - (as a piecewise meromorphic matrix-valued function). An explicit solution of the Wiener-Hopf factorization problem for a(t) is obtained and the partial factorization indices of a(t) are calculated. Here an explicit solution of a factorization problem is meant in the sense of reducing it to the investigation of finitely many systems of linear algebraic equations with matrices expressed in closed form, that is, in quadratures. Bibliography: 15 titles.

Compressive Sensing Based Bayesian Sparse Channel Estimation for OFDM Communication Systems: High Performance and Low Complexity

Science.gov (United States)

Xu, Li; Shan, Lin; Adachi, Fumiyuki

2014-01-01

In orthogonal frequency division modulation (OFDM) communication systems, channel state information (CSI) is required at receiver due to the fact that frequency-selective fading channel leads to disgusting intersymbol interference (ISI) over data transmission. Broadband channel model is often described by very few dominant channel taps and they can be probed by compressive sensing based sparse channel estimation (SCE) methods, for example, orthogonal matching pursuit algorithm, which can take the advantage of sparse structure effectively in the channel as for prior information. However, these developed methods are vulnerable to both noise interference and column coherence of training signal matrix. In other words, the primary objective of these conventional methods is to catch the dominant channel taps without a report of posterior channel uncertainty. To improve the estimation performance, we proposed a compressive sensing based Bayesian sparse channel estimation (BSCE) method which cannot only exploit the channel sparsity but also mitigate the unexpected channel uncertainty without scarifying any computational complexity. The proposed method can reveal potential ambiguity among multiple channel estimators that are ambiguous due to observation noise or correlation interference among columns in the training matrix. Computer simulations show that proposed method can improve the estimation performance when comparing with conventional SCE methods. PMID:24983012

Fast matrix factorization algorithm for DOSY based on the eigenvalue decomposition and the difference approximation focusing on the size of observed matrix

International Nuclear Information System (INIS)

Tanaka, Yuho; Uruma, Kazunori; Furukawa, Toshihiro; Nakao, Tomoki; Izumi, Kenya; Utsumi, Hiroaki

2017-01-01

This paper deals with an analysis problem for diffusion-ordered NMR spectroscopy (DOSY). DOSY is formulated as a matrix factorization problem of a given observed matrix. In order to solve this problem, a direct exponential curve resolution algorithm (DECRA) is well known. DECRA is based on singular value decomposition; the advantage of this algorithm is that the initial value is not required. However, DECRA requires a long calculating time, depending on the size of the given observed matrix due to the singular value decomposition, and this is a serious problem in practical use. Thus, this paper proposes a new analysis algorithm for DOSY to achieve a short calculating time. In order to solve matrix factorization for DOSY without using singular value decomposition, this paper focuses on the size of the given observed matrix. The observed matrix in DOSY is also a rectangular matrix with more columns than rows, due to limitation of the measuring time; thus, the proposed algorithm transforms the given observed matrix into a small observed matrix. The proposed algorithm applies the eigenvalue decomposition and the difference approximation to the small observed matrix, and the matrix factorization problem for DOSY is solved. The simulation and a data analysis show that the proposed algorithm achieves a lower calculating time than DECRA as well as similar analysis result results to DECRA. (author)

Multiplicative algorithms for constrained non-negative matrix factorization

KAUST Repository

Peng, Chengbin; Wong, Kachun; Rockwood, Alyn; Zhang, Xiangliang; Jiang, Jinling; Keyes, David E.

2012-01-01

Non-negative matrix factorization (NMF) provides the advantage of parts-based data representation through additive only combinations. It has been widely adopted in areas like item recommending, text mining, data clustering, speech denoising, etc

Cross-correlation matrix analysis of Chinese and American bank stocks in subprime crisis

International Nuclear Information System (INIS)

Zhu Shi-Zhao; Li Xin-Li; Zhang Wen-Qing; Wang Bing-Hong; Nie Sen; Yu Gao-Feng; Han Xiao-Pu

2015-01-01

In order to study the universality of the interactions among different markets, we analyze the cross-correlation matrix of the price of the Chinese and American bank stocks. We then find that the stock prices of the emerging market are more correlated than that of the developed market. Considering that the values of the components for the eigenvector may be positive or negative, we analyze the differences between two markets in combination with the endogenous and exogenous events which influence the financial markets. We find that the sparse pattern of components of eigenvectors out of the threshold value has no change in American bank stocks before and after the subprime crisis. However, it changes from sparse to dense for Chinese bank stocks. By using the threshold value to exclude the external factors, we simulate the interactions in financial markets. (paper)

Estimation in a multiplicative mixed model involving a genetic relationship matrix

Directory of Open Access Journals (Sweden)

Eccleston John A

2009-04-01

Full Text Available Abstract Genetic models partitioning additive and non-additive genetic effects for populations tested in replicated multi-environment trials (METs in a plant breeding program have recently been presented in the literature. For these data, the variance model involves the direct product of a large numerator relationship matrix A, and a complex structure for the genotype by environment interaction effects, generally of a factor analytic (FA form. With MET data, we expect a high correlation in genotype rankings between environments, leading to non-positive definite covariance matrices. Estimation methods for reduced rank models have been derived for the FA formulation with independent genotypes, and we employ these estimation methods for the more complex case involving the numerator relationship matrix. We examine the performance of differing genetic models for MET data with an embedded pedigree structure, and consider the magnitude of the non-additive variance. The capacity of existing software packages to fit these complex models is largely due to the use of the sparse matrix methodology and the average information algorithm. Here, we present an extension to the standard formulation necessary for estimation with a factor analytic structure across multiple environments.

Fast Sparse Coding for Range Data Denoising with Sparse Ridges Constraint

Directory of Open Access Journals (Sweden)

Zhi Gao

2018-05-01

Full Text Available Light detection and ranging (LiDAR sensors have been widely deployed on intelligent systems such as unmanned ground vehicles (UGVs and unmanned aerial vehicles (UAVs to perform localization, obstacle detection, and navigation tasks. Thus, research into range data processing with competitive performance in terms of both accuracy and efficiency has attracted increasing attention. Sparse coding has revolutionized signal processing and led to state-of-the-art performance in a variety of applications. However, dictionary learning, which plays the central role in sparse coding techniques, is computationally demanding, resulting in its limited applicability in real-time systems. In this study, we propose sparse coding algorithms with a fixed pre-learned ridge dictionary to realize range data denoising via leveraging the regularity of laser range measurements in man-made environments. Experiments on both synthesized data and real data demonstrate that our method obtains accuracy comparable to that of sophisticated sparse coding methods, but with much higher computational efficiency.

Fast Sparse Coding for Range Data Denoising with Sparse Ridges Constraint.

Science.gov (United States)

Gao, Zhi; Lao, Mingjie; Sang, Yongsheng; Wen, Fei; Ramesh, Bharath; Zhai, Ruifang

2018-05-06

Light detection and ranging (LiDAR) sensors have been widely deployed on intelligent systems such as unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs) to perform localization, obstacle detection, and navigation tasks. Thus, research into range data processing with competitive performance in terms of both accuracy and efficiency has attracted increasing attention. Sparse coding has revolutionized signal processing and led to state-of-the-art performance in a variety of applications. However, dictionary learning, which plays the central role in sparse coding techniques, is computationally demanding, resulting in its limited applicability in real-time systems. In this study, we propose sparse coding algorithms with a fixed pre-learned ridge dictionary to realize range data denoising via leveraging the regularity of laser range measurements in man-made environments. Experiments on both synthesized data and real data demonstrate that our method obtains accuracy comparable to that of sophisticated sparse coding methods, but with much higher computational efficiency.

When sparse coding meets ranking: a joint framework for learning sparse codes and ranking scores

KAUST Repository

Wang, Jim Jing-Yan

2017-06-28

Sparse coding, which represents a data point as a sparse reconstruction code with regard to a dictionary, has been a popular data representation method. Meanwhile, in database retrieval problems, learning the ranking scores from data points plays an important role. Up to now, these two problems have always been considered separately, assuming that data coding and ranking are two independent and irrelevant problems. However, is there any internal relationship between sparse coding and ranking score learning? If yes, how to explore and make use of this internal relationship? In this paper, we try to answer these questions by developing the first joint sparse coding and ranking score learning algorithm. To explore the local distribution in the sparse code space, and also to bridge coding and ranking problems, we assume that in the neighborhood of each data point, the ranking scores can be approximated from the corresponding sparse codes by a local linear function. By considering the local approximation error of ranking scores, the reconstruction error and sparsity of sparse coding, and the query information provided by the user, we construct a unified objective function for learning of sparse codes, the dictionary and ranking scores. We further develop an iterative algorithm to solve this optimization problem.

Low-Complexity Bayesian Estimation of Cluster-Sparse Channels

KAUST Repository

Ballal, Tarig

2015-09-18

This paper addresses the problem of channel impulse response estimation for cluster-sparse channels under the Bayesian estimation framework. We develop a novel low-complexity minimum mean squared error (MMSE) estimator by exploiting the sparsity of the received signal profile and the structure of the measurement matrix. It is shown that due to the banded Toeplitz/circulant structure of the measurement matrix, a channel impulse response, such as underwater acoustic channel impulse responses, can be partitioned into a number of orthogonal or approximately orthogonal clusters. The orthogonal clusters, the sparsity of the channel impulse response and the structure of the measurement matrix, all combined, result in a computationally superior realization of the MMSE channel estimator. The MMSE estimator calculations boil down to simpler in-cluster calculations that can be reused in different clusters. The reduction in computational complexity allows for a more accurate implementation of the MMSE estimator. The proposed approach is tested using synthetic Gaussian channels, as well as simulated underwater acoustic channels. Symbol-error-rate performance and computation time confirm the superiority of the proposed method compared to selected benchmark methods in systems with preamble-based training signals transmitted over clustersparse channels.

Low-Complexity Bayesian Estimation of Cluster-Sparse Channels

KAUST Repository

Ballal, Tarig; Al-Naffouri, Tareq Y.; Ahmed, Syed

2015-01-01

This paper addresses the problem of channel impulse response estimation for cluster-sparse channels under the Bayesian estimation framework. We develop a novel low-complexity minimum mean squared error (MMSE) estimator by exploiting the sparsity of the received signal profile and the structure of the measurement matrix. It is shown that due to the banded Toeplitz/circulant structure of the measurement matrix, a channel impulse response, such as underwater acoustic channel impulse responses, can be partitioned into a number of orthogonal or approximately orthogonal clusters. The orthogonal clusters, the sparsity of the channel impulse response and the structure of the measurement matrix, all combined, result in a computationally superior realization of the MMSE channel estimator. The MMSE estimator calculations boil down to simpler in-cluster calculations that can be reused in different clusters. The reduction in computational complexity allows for a more accurate implementation of the MMSE estimator. The proposed approach is tested using synthetic Gaussian channels, as well as simulated underwater acoustic channels. Symbol-error-rate performance and computation time confirm the superiority of the proposed method compared to selected benchmark methods in systems with preamble-based training signals transmitted over clustersparse channels.

Fast Solution in Sparse LDA for Binary Classification

Science.gov (United States)

Moghaddam, Baback

2010-01-01

An algorithm that performs sparse linear discriminant analysis (Sparse-LDA) finds near-optimal solutions in far less time than the prior art when specialized to binary classification (of 2 classes). Sparse-LDA is a type of feature- or variable- selection problem with numerous applications in statistics, machine learning, computer vision, computational finance, operations research, and bio-informatics. Because of its combinatorial nature, feature- or variable-selection problems are NP-hard or computationally intractable in cases involving more than 30 variables or features. Therefore, one typically seeks approximate solutions by means of greedy search algorithms. The prior Sparse-LDA algorithm was a greedy algorithm that considered the best variable or feature to add/ delete to/ from its subsets in order to maximally discriminate between multiple classes of data. The present algorithm is designed for the special but prevalent case of 2-class or binary classification (e.g. 1 vs. 0, functioning vs. malfunctioning, or change versus no change). The present algorithm provides near-optimal solutions on large real-world datasets having hundreds or even thousands of variables or features (e.g. selecting the fewest wavelength bands in a hyperspectral sensor to do terrain classification) and does so in typical computation times of minutes as compared to days or weeks as taken by the prior art. Sparse LDA requires solving generalized eigenvalue problems for a large number of variable subsets (represented by the submatrices of the input within-class and between-class covariance matrices). In the general (fullrank) case, the amount of computation scales at least cubically with the number of variables and thus the size of the problems that can be solved is limited accordingly. However, in binary classification, the principal eigenvalues can be found using a special analytic formula, without resorting to costly iterative techniques. The present algorithm exploits this analytic

Form factors in quantum integrable models with GL(3)-invariant R-matrix

Energy Technology Data Exchange (ETDEWEB)

Pakuliak, S., E-mail: pakuliak@theor.jinr.ru [Laboratory of Theoretical Physics, JINR, 141980 Dubna, Moscow Reg. (Russian Federation); Moscow Institute of Physics and Technology, 141700 Dolgoprudny, Moscow Reg. (Russian Federation); Institute of Theoretical and Experimental Physics, 117259 Moscow (Russian Federation); Ragoucy, E., E-mail: eric.ragoucy@lapth.cnrs.fr [Laboratoire de Physique Théorique LAPTH, CNRS and Université de Savoie, BP 110, 74941 Annecy-le-Vieux Cedex (France); Slavnov, N.A., E-mail: nslavnov@mi.ras.ru [Steklov Mathematical Institute, Moscow (Russian Federation)

2014-04-15

We study integrable models solvable by the nested algebraic Bethe ansatz and possessing GL(3)-invariant R-matrix. We obtain determinant representations for form factors of off-diagonal entries of the monodromy matrix. These representations can be used for the calculation of form factors and correlation functions of the XXX SU(3)-invariant Heisenberg chain.

A fast sparse reconstruction algorithm for electrical tomography

International Nuclear Information System (INIS)

Zhao, Jia; Xu, Yanbin; Tan, Chao; Dong, Feng

2014-01-01

Electrical tomography (ET) has been widely investigated due to its advantages of being non-radiative, low-cost and high-speed. However, the image reconstruction of ET is a nonlinear and ill-posed inverse problem and the imaging results are easily affected by measurement noise. A sparse reconstruction algorithm based on L 1 regularization is robust to noise and consequently provides a high quality of reconstructed images. In this paper, a sparse reconstruction by separable approximation algorithm (SpaRSA) is extended to solve the ET inverse problem. The algorithm is competitive with the fastest state-of-the-art algorithms in solving the standard L 2 −L 1 problem. However, it is computationally expensive when the dimension of the matrix is large. To further improve the calculation speed of solving inverse problems, a projection method based on the Krylov subspace is employed and combined with the SpaRSA algorithm. The proposed algorithm is tested with image reconstruction of electrical resistance tomography (ERT). Both simulation and experimental results demonstrate that the proposed method can reduce the computational time and improve the noise robustness for the image reconstruction. (paper)

Multiple Kernel Learning for adaptive graph regularized nonnegative matrix factorization

KAUST Repository

Wang, Jim Jing-Yan; AbdulJabbar, Mustafa Abdulmajeed

2012-01-01

Nonnegative Matrix Factorization (NMF) has been continuously evolving in several areas like pattern recognition and information retrieval methods. It factorizes a matrix into a product of 2 low-rank non-negative matrices that will define parts-based, and linear representation of non-negative data. Recently, Graph regularized NMF (GrNMF) is proposed to find a compact representation, which uncovers the hidden semantics and simultaneously respects the intrinsic geometric structure. In GNMF, an affinity graph is constructed from the original data space to encode the geometrical information. In this paper, we propose a novel idea which engages a Multiple Kernel Learning approach into refining the graph structure that reflects the factorization of the matrix and the new data space. The GrNMF is improved by utilizing the graph refined by the kernel learning, and then a novel kernel learning method is introduced under the GrNMF framework. Our approach shows encouraging results of the proposed algorithm in comparison to the state-of-the-art clustering algorithms like NMF, GrNMF, SVD etc.

Completing sparse and disconnected protein-protein network by deep learning.

Science.gov (United States)

Huang, Lei; Liao, Li; Wu, Cathy H

2018-03-22

Protein-protein interaction (PPI) prediction remains a central task in systems biology to achieve a better and holistic understanding of cellular and intracellular processes. Recently, an increasing number of computational methods have shifted from pair-wise prediction to network level prediction. Many of the existing network level methods predict PPIs under the assumption that the training network should be connected. However, this assumption greatly affects the prediction power and limits the application area because the current golden standard PPI networks are usually very sparse and disconnected. Therefore, how to effectively predict PPIs based on a training network that is sparse and disconnected remains a challenge. In this work, we developed a novel PPI prediction method based on deep learning neural network and regularized Laplacian kernel. We use a neural network with an autoencoder-like architecture to implicitly simulate the evolutionary processes of a PPI network. Neurons of the output layer correspond to proteins and are labeled with values (1 for interaction and 0 for otherwise) from the adjacency matrix of a sparse disconnected training PPI network. Unlike autoencoder, neurons at the input layer are given all zero input, reflecting an assumption of no a priori knowledge about PPIs, and hidden layers of smaller sizes mimic ancient interactome at different times during evolution. After the training step, an evolved PPI network whose rows are outputs of the neural network can be obtained. We then predict PPIs by applying the regularized Laplacian kernel to the transition matrix that is built upon the evolved PPI network. The results from cross-validation experiments show that the PPI prediction accuracies for yeast data and human data measured as AUC are increased by up to 8.4 and 14.9% respectively, as compared to the baseline. Moreover, the evolved PPI network can also help us leverage complementary information from the disconnected training network

Exploiting Data Sparsity In Covariance Matrix Computations on Heterogeneous Systems

KAUST Repository

Charara, Ali M.

2018-05-24

Covariance matrices are ubiquitous in computational sciences, typically describing the correlation of elements of large multivariate spatial data sets. For example, covari- ance matrices are employed in climate/weather modeling for the maximum likelihood estimation to improve prediction, as well as in computational ground-based astronomy to enhance the observed image quality by filtering out noise produced by the adap- tive optics instruments and atmospheric turbulence. The structure of these covariance matrices is dense, symmetric, positive-definite, and often data-sparse, therefore, hier- archically of low-rank. This thesis investigates the performance limit of dense matrix computations (e.g., Cholesky factorization) on covariance matrix problems as the number of unknowns grows, and in the context of the aforementioned applications. We employ recursive formulations of some of the basic linear algebra subroutines (BLAS) to accelerate the covariance matrix computation further, while reducing data traffic across the memory subsystems layers. However, dealing with large data sets (i.e., covariance matrices of billions in size) can rapidly become prohibitive in memory footprint and algorithmic complexity. Most importantly, this thesis investigates the tile low-rank data format (TLR), a new compressed data structure and layout, which is valuable in exploiting data sparsity by approximating the operator. The TLR com- pressed data structure allows approximating the original problem up to user-defined numerical accuracy. This comes at the expense of dealing with tasks with much lower arithmetic intensities than traditional dense computations. In fact, this thesis con- solidates the two trends of dense and data-sparse linear algebra for HPC. Not only does the thesis leverage recursive formulations for dense Cholesky-based matrix al- gorithms, but it also implements a novel TLR-Cholesky factorization using batched linear algebra operations to increase hardware occupancy and

Implicit vs. Explicit Trust in Social Matrix Factorization

NARCIS (Netherlands)

Fazeli, Soude; Loni, Babak; Bellogin, Alejandro; Drachsler, Hendrik; Sloep, Peter

2014-01-01

Incorporating social trust in Matrix Factorization (MF) methods demonstrably improves accuracy of rating prediction. Such approaches mainly use the trust scores explicitly expressed by users. However, it is often challenging to have users provide explicit trust scores of each other. There exist

Sparse structure regularized ranking

KAUST Repository

Wang, Jim Jing-Yan; Sun, Yijun; Gao, Xin

2014-01-01

Learning ranking scores is critical for the multimedia database retrieval problem. In this paper, we propose a novel ranking score learning algorithm by exploring the sparse structure and using it to regularize ranking scores. To explore the sparse

Sparse structure regularized ranking

KAUST Repository

Wang, Jim Jing-Yan

2014-04-17

Learning ranking scores is critical for the multimedia database retrieval problem. In this paper, we propose a novel ranking score learning algorithm by exploring the sparse structure and using it to regularize ranking scores. To explore the sparse structure, we assume that each multimedia object could be represented as a sparse linear combination of all other objects, and combination coefficients are regarded as a similarity measure between objects and used to regularize their ranking scores. Moreover, we propose to learn the sparse combination coefficients and the ranking scores simultaneously. A unified objective function is constructed with regard to both the combination coefficients and the ranking scores, and is optimized by an iterative algorithm. Experiments on two multimedia database retrieval data sets demonstrate the significant improvements of the propose algorithm over state-of-the-art ranking score learning algorithms.

Diffusion Indexes With Sparse Loadings

DEFF Research Database (Denmark)

Kristensen, Johannes Tang

2017-01-01

The use of large-dimensional factor models in forecasting has received much attention in the literature with the consensus being that improvements on forecasts can be achieved when comparing with standard models. However, recent contributions in the literature have demonstrated that care needs...... to the problem by using the least absolute shrinkage and selection operator (LASSO) as a variable selection method to choose between the possible variables and thus obtain sparse loadings from which factors or diffusion indexes can be formed. This allows us to build a more parsimonious factor model...... in forecasting accuracy and thus find it to be an important alternative to PC. Supplementary materials for this article are available online....

General factorization relations and consistency conditions in the sudden approximation via infinite matrix inversion

International Nuclear Information System (INIS)

Chan, C.K.; Hoffman, D.K.; Evans, J.W.

1985-01-01

Local, i.e., multiplicative, operators satisfy well-known linear factorization relations wherein matrix elements (between states associated with a complete set of wave functions) can be obtained as a linear combination of those out of the ground state (the input data). Analytic derivation of factorization relations for general state input data results in singular integral expressions for the coefficients, which can, however, be regularized using consistency conditions between matrix elements out of a single (nonground) state. Similar results hold for suitable ''symmetry class'' averaged matrix elements where the symmetry class projection operators are ''complete.'' In several cases where the wave functions or projection operators incorporate orthogonal polynomial dependence, we show that the ground state factorization relations have a simplified structure allowing an alternative derivation of the general factorization relations via an infinite matrix inversion procedure. This form is shown to have some advantages over previous versions. In addition, this matrix inversion procedure obtains all consistency conditions (which is not always the case from regularization of singular integrals)

Turbulent flows over sparse canopies

Science.gov (United States)

Sharma, Akshath; García-Mayoral, Ricardo

2018-04-01

Turbulent flows over sparse and dense canopies exerting a similar drag force on the flow are investigated using Direct Numerical Simulations. The dense canopies are modelled using a homogeneous drag force, while for the sparse canopy, the geometry of the canopy elements is represented. It is found that on using the friction velocity based on the local shear at each height, the streamwise velocity fluctuations and the Reynolds stress within the sparse canopy are similar to those from a comparable smooth-wall case. In addition, when scaled with the local friction velocity, the intensity of the off-wall peak in the streamwise vorticity for sparse canopies also recovers a value similar to a smooth-wall. This indicates that the sparse canopy does not significantly disturb the near-wall turbulence cycle, but causes its rescaling to an intensity consistent with a lower friction velocity within the canopy. In comparison, the dense canopy is found to have a higher damping effect on the turbulent fluctuations. For the case of the sparse canopy, a peak in the spectral energy density of the wall-normal velocity, and Reynolds stress is observed, which may indicate the formation of Kelvin-Helmholtz-like instabilities. It is also found that a sparse canopy is better modelled by a homogeneous drag applied on the mean flow alone, and not the turbulent fluctuations.

Strong factor in the SO(2,3) S matrix

International Nuclear Information System (INIS)

Amado, R.D.; Sparrow, D.A.

1986-01-01

The group theoretic S matrix of Alhassid, Iachello, and Wu is factorable into a product of Coulomb and strong factors. The strong factor is examined with a view to relating it to more fa- miliar potential and phase shift descriptions. We find simple approximate expressions for the phase shifts which are very accurate for heavy-ion-type applications. For peripheral scattering it is possible to obtain simple expressions relating the strong factor to an effective potential

Integrative analysis of multiple diverse omics datasets by sparse group multitask regression

Directory of Open Access Journals (Sweden)

Dongdong eLin

2014-10-01

Full Text Available A variety of high throughput genome-wide assays enable the exploration of genetic risk factors underlying complex traits. Although these studies have remarkable impact on identifying susceptible biomarkers, they suffer from issues such as limited sample size and low reproducibility. Combining individual studies of different genetic levels/platforms has the promise to improve the power and consistency of biomarker identification. In this paper, we propose a novel integrative method, namely sparse group multitask regression, for integrating diverse omics datasets, platforms and populations to identify risk genes/factors of complex diseases. This method combines multitask learning with sparse group regularization, which will: 1 treat the biomarker identification in each single study as a task and then combine them by multitask learning; 2 group variables from all studies for identifying significant genes; 3 enforce sparse constraint on groups of variables to overcome the ‘small sample, but large variables’ problem. We introduce two sparse group penalties: sparse group lasso and sparse group ridge in our multitask model, and provide an effective algorithm for each model. In addition, we propose a significance test for the identification of potential risk genes. Two simulation studies are performed to evaluate the performance of our integrative method by comparing it with conventional meta-analysis method. The results show that our sparse group multitask method outperforms meta-analysis method significantly. In an application to our osteoporosis studies, 7 genes are identified as significant genes by our method and are found to have significant effects in other three independent studies for validation. The most significant gene SOD2 has been identified in our previous osteoporosis study involving the same expression dataset. Several other genes such as TREML2, HTR1E and GLO1 are shown to be novel susceptible genes for osteoporosis, as confirmed

Sparse random matrices: The eigenvalue spectrum revisited

International Nuclear Information System (INIS)

Semerjian, Guilhem; Cugliandolo, Leticia F.

2003-08-01

We revisit the derivation of the density of states of sparse random matrices. We derive a recursion relation that allows one to compute the spectrum of the matrix of incidence for finite trees that determines completely the low concentration limit. Using the iterative scheme introduced by Biroli and Monasson [J. Phys. A 32, L255 (1999)] we find an approximate expression for the density of states expected to hold exactly in the opposite limit of large but finite concentration. The combination of the two methods yields a very simple geometric interpretation of the tails of the spectrum. We test the analytic results with numerical simulations and we suggest an indirect numerical method to explore the tails of the spectrum. (author)

Compressive sensing using optimized sensing matrix for face verification

Science.gov (United States)

Oey, Endra; Jeffry; Wongso, Kelvin; Tommy

2017-12-01

Biometric appears as one of the solutions which is capable in solving problems that occurred in the usage of password in terms of data access, for example there is possibility in forgetting password and hard to recall various different passwords. With biometrics, physical characteristics of a person can be captured and used in the identification process. In this research, facial biometric is used in the verification process to determine whether the user has the authority to access the data or not. Facial biometric is chosen as its low cost implementation and generate quite accurate result for user identification. Face verification system which is adopted in this research is Compressive Sensing (CS) technique, in which aims to reduce dimension size as well as encrypt data in form of facial test image where the image is represented in sparse signals. Encrypted data can be reconstructed using Sparse Coding algorithm. Two types of Sparse Coding namely Orthogonal Matching Pursuit (OMP) and Iteratively Reweighted Least Squares -ℓp (IRLS-ℓp) will be used for comparison face verification system research. Reconstruction results of sparse signals are then used to find Euclidean norm with the sparse signal of user that has been previously saved in system to determine the validity of the facial test image. Results of system accuracy obtained in this research are 99% in IRLS with time response of face verification for 4.917 seconds and 96.33% in OMP with time response of face verification for 0.4046 seconds with non-optimized sensing matrix, while 99% in IRLS with time response of face verification for 13.4791 seconds and 98.33% for OMP with time response of face verification for 3.1571 seconds with optimized sensing matrix.

Discriminative sparse coding on multi-manifolds

KAUST Repository

Wang, J.J.-Y.; Bensmail, H.; Yao, N.; Gao, Xin

2013-01-01

Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics. However, the conventional sparse coding algorithms and their manifold-regularized variants (graph sparse coding and Laplacian sparse coding), learn codebooks and codes in an unsupervised manner and neglect class information that is available in the training set. To address this problem, we propose a novel discriminative sparse coding method based on multi-manifolds, that learns discriminative class-conditioned codebooks and sparse codes from both data feature spaces and class labels. First, the entire training set is partitioned into multiple manifolds according to the class labels. Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditioned codebooks and codes to maximize the manifold margins of different classes. Lastly, we present a data sample-manifold matching-based strategy to classify the unlabeled data samples. Experimental results on somatic mutations identification and breast tumor classification based on ultrasonic images demonstrate the efficacy of the proposed data representation and classification approach. 2013 The Authors. All rights reserved.

Discriminative sparse coding on multi-manifolds

KAUST Repository

Wang, J.J.-Y.

2013-09-26

Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics. However, the conventional sparse coding algorithms and their manifold-regularized variants (graph sparse coding and Laplacian sparse coding), learn codebooks and codes in an unsupervised manner and neglect class information that is available in the training set. To address this problem, we propose a novel discriminative sparse coding method based on multi-manifolds, that learns discriminative class-conditioned codebooks and sparse codes from both data feature spaces and class labels. First, the entire training set is partitioned into multiple manifolds according to the class labels. Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditioned codebooks and codes to maximize the manifold margins of different classes. Lastly, we present a data sample-manifold matching-based strategy to classify the unlabeled data samples. Experimental results on somatic mutations identification and breast tumor classification based on ultrasonic images demonstrate the efficacy of the proposed data representation and classification approach. 2013 The Authors. All rights reserved.

Sparse Regression by Projection and Sparse Discriminant Analysis

KAUST Repository

Qi, Xin

2015-04-03

© 2015, © American Statistical Association, Institute of Mathematical Statistics, and Interface Foundation of North America. Recent years have seen active developments of various penalized regression methods, such as LASSO and elastic net, to analyze high-dimensional data. In these approaches, the direction and length of the regression coefficients are determined simultaneously. Due to the introduction of penalties, the length of the estimates can be far from being optimal for accurate predictions. We introduce a new framework, regression by projection, and its sparse version to analyze high-dimensional data. The unique nature of this framework is that the directions of the regression coefficients are inferred first, and the lengths and the tuning parameters are determined by a cross-validation procedure to achieve the largest prediction accuracy. We provide a theoretical result for simultaneous model selection consistency and parameter estimation consistency of our method in high dimension. This new framework is then generalized such that it can be applied to principal components analysis, partial least squares, and canonical correlation analysis. We also adapt this framework for discriminant analysis. Compared with the existing methods, where there is relatively little control of the dependency among the sparse components, our method can control the relationships among the components. We present efficient algorithms and related theory for solving the sparse regression by projection problem. Based on extensive simulations and real data analysis, we demonstrate that our method achieves good predictive performance and variable selection in the regression setting, and the ability to control relationships between the sparse components leads to more accurate classification. In supplementary materials available online, the details of the algorithms and theoretical proofs, and R codes for all simulation studies are provided.

Sparse distributed memory overview

Science.gov (United States)

Raugh, Mike

1990-01-01

The Sparse Distributed Memory (SDM) project is investigating the theory and applications of massively parallel computing architecture, called sparse distributed memory, that will support the storage and retrieval of sensory and motor patterns characteristic of autonomous systems. The immediate objectives of the project are centered in studies of the memory itself and in the use of the memory to solve problems in speech, vision, and robotics. Investigation of methods for encoding sensory data is an important part of the research. Examples of NASA missions that may benefit from this work are Space Station, planetary rovers, and solar exploration. Sparse distributed memory offers promising technology for systems that must learn through experience and be capable of adapting to new circumstances, and for operating any large complex system requiring automatic monitoring and control. Sparse distributed memory is a massively parallel architecture motivated by efforts to understand how the human brain works. Sparse distributed memory is an associative memory, able to retrieve information from cues that only partially match patterns stored in the memory. It is able to store long temporal sequences derived from the behavior of a complex system, such as progressive records of the system's sensory data and correlated records of the system's motor controls.

Technical note: Avoiding the direct inversion of the numerator relationship matrix for genotyped animals in single-step genomic best linear unbiased prediction solved with the preconditioned conjugate gradient.

Science.gov (United States)

Masuda, Y; Misztal, I; Legarra, A; Tsuruta, S; Lourenco, D A L; Fragomeni, B O; Aguilar, I

2017-01-01

This paper evaluates an efficient implementation to multiply the inverse of a numerator relationship matrix for genotyped animals () by a vector (). The computation is required for solving mixed model equations in single-step genomic BLUP (ssGBLUP) with the preconditioned conjugate gradient (PCG). The inverse can be decomposed into sparse matrices that are blocks of the sparse inverse of a numerator relationship matrix () including genotyped animals and their ancestors. The elements of were rapidly calculated with the Henderson's rule and stored as sparse matrices in memory. Implementation of was by a series of sparse matrix-vector multiplications. Diagonal elements of , which were required as preconditioners in PCG, were approximated with a Monte Carlo method using 1,000 samples. The efficient implementation of was compared with explicit inversion of with 3 data sets including about 15,000, 81,000, and 570,000 genotyped animals selected from populations with 213,000, 8.2 million, and 10.7 million pedigree animals, respectively. The explicit inversion required 1.8 GB, 49 GB, and 2,415 GB (estimated) of memory, respectively, and 42 s, 56 min, and 13.5 d (estimated), respectively, for the computations. The efficient implementation required <1 MB, 2.9 GB, and 2.3 GB of memory, respectively, and <1 sec, 3 min, and 5 min, respectively, for setting up. Only <1 sec was required for the multiplication in each PCG iteration for any data sets. When the equations in ssGBLUP are solved with the PCG algorithm, is no longer a limiting factor in the computations.

In-place sparse suffix sorting

DEFF Research Database (Denmark)

Prezza, Nicola

2018-01-01

information regarding the lexicographical order of a size-b subset of all n text suffixes is often needed. Such information can be stored space-efficiently (in b words) in the sparse suffix array (SSA). The SSA and its relative sparse LCP array (SLCP) can be used as a space-efficient substitute of the sparse...... suffix tree. Very recently, Gawrychowski and Kociumaka [11] showed that the sparse suffix tree (and therefore SSA and SLCP) can be built in asymptotically optimal O(b) space with a Monte Carlo algorithm running in O(n) time. The main reason for using the SSA and SLCP arrays in place of the sparse suffix...... tree is, however, their reduced space of b words each. This leads naturally to the quest for in-place algorithms building these arrays. Franceschini and Muthukrishnan [8] showed that the full suffix array can be built in-place and in optimal running time. On the other hand, finding sub-quadratic in...

Image Super-Resolution Algorithm Based on an Improved Sparse Autoencoder

Directory of Open Access Journals (Sweden)

Detian Huang

2018-01-01

Full Text Available Due to the limitations of the resolution of the imaging system and the influence of scene changes and other factors, sometimes only low-resolution images can be acquired, which cannot satisfy the practical application’s requirements. To improve the quality of low-resolution images, a novel super-resolution algorithm based on an improved sparse autoencoder is proposed. Firstly, in the training set preprocessing stage, the high- and low-resolution image training sets are constructed, respectively, by using high-frequency information of the training samples as the characterization, and then the zero-phase component analysis whitening technique is utilized to decorrelate the formed joint training set to reduce its redundancy. Secondly, a constructed sparse regularization term is added to the cost function of the traditional sparse autoencoder to further strengthen the sparseness constraint on the hidden layer. Finally, in the dictionary learning stage, the improved sparse autoencoder is adopted to achieve unsupervised dictionary learning to improve the accuracy and stability of the dictionary. Experimental results validate that the proposed algorithm outperforms the existing algorithms both in terms of the subjective visual perception and the objective evaluation indices, including the peak signal-to-noise ratio and the structural similarity measure.

Non-negative matrix factorization in texture feature for classification of dementia with MRI data

Science.gov (United States)

Sarwinda, D.; Bustamam, A.; Ardaneswari, G.

2017-07-01

This paper investigates applications of non-negative matrix factorization as feature selection method to select the features from gray level co-occurrence matrix. The proposed approach is used to classify dementia using MRI data. In this study, texture analysis using gray level co-occurrence matrix is done to feature extraction. In the feature extraction process of MRI data, we found seven features from gray level co-occurrence matrix. Non-negative matrix factorization selected three features that influence of all features produced by feature extractions. A Naïve Bayes classifier is adapted to classify dementia, i.e. Alzheimer's disease, Mild Cognitive Impairment (MCI) and normal control. The experimental results show that non-negative factorization as feature selection method able to achieve an accuracy of 96.4% for classification of Alzheimer's and normal control. The proposed method also compared with other features selection methods i.e. Principal Component Analysis (PCA).

Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding

Science.gov (United States)

Moody, Daniela; Wohlberg, Brendt

2018-01-02

An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detect geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.

Constructing the tree-level Yang-Mills S-matrix using complex factorization

Science.gov (United States)

Schuster, Philip C.; Toro, Natalia

2009-06-01

A remarkable connection between BCFW recursion relations and constraints on the S-matrix was made by Benincasa and Cachazo in 0705.4305, who noted that mutual consistency of different BCFW constructions of four-particle amplitudes generates non-trivial (but familiar) constraints on three-particle coupling constants — these include gauge invariance, the equivalence principle, and the lack of non-trivial couplings for spins > 2. These constraints can also be derived with weaker assumptions, by demanding the existence of four-point amplitudes that factorize properly in all unitarity limits with complex momenta. From this starting point, we show that the BCFW prescription can be interpreted as an algorithm for fully constructing a tree-level S-matrix, and that complex factorization of general BCFW amplitudes follows from the factorization of four-particle amplitudes. The allowed set of BCFW deformations is identified, formulated entirely as a statement on the three-particle sector, and using only complex factorization as a guide. Consequently, our analysis based on the physical consistency of the S-matrix is entirely independent of field theory. We analyze the case of pure Yang-Mills, and outline a proof for gravity. For Yang-Mills, we also show that the well-known scaling behavior of BCFW-deformed amplitudes at large z is a simple consequence of factorization. For gravity, factorization in certain channels requires asymptotic behavior ~ 1/z2.

Constructing the tree-level Yang-Mills S-matrix using complex factorization

International Nuclear Information System (INIS)

Schuster, Philip C.; Toro, Natalia

2009-01-01

A remarkable connection between BCFW recursion relations and constraints on the S-matrix was made by Benincasa and Cachazo in 0705.4305, who noted that mutual consistency of different BCFW constructions of four-particle amplitudes generates non-trivial (but familiar) constraints on three-particle coupling constants - these include gauge invariance, the equivalence principle, and the lack of non-trivial couplings for spins > 2. These constraints can also be derived with weaker assumptions, by demanding the existence of four-point amplitudes that factorize properly in all unitarity limits with complex momenta. From this starting point, we show that the BCFW prescription can be interpreted as an algorithm for fully constructing a tree-level S-matrix, and that complex factorization of general BCFW amplitudes follows from the factorization of four-particle amplitudes. The allowed set of BCFW deformations is identified, formulated entirely as a statement on the three-particle sector, and using only complex factorization as a guide. Consequently, our analysis based on the physical consistency of the S-matrix is entirely independent of field theory. We analyze the case of pure Yang-Mills, and outline a proof for gravity. For Yang-Mills, we also show that the well-known scaling behavior of BCFW-deformed amplitudes at large z is a simple consequence of factorization. For gravity, factorization in certain channels requires asymptotic behavior ∼ 1/z 2 .

Threshold partitioning of sparse matrices and applications to Markov chains

Energy Technology Data Exchange (ETDEWEB)

Choi, Hwajeong; Szyld, D.B. [Temple Univ., Philadelphia, PA (United States)

1996-12-31

It is well known that the order of the variables and equations of a large, sparse linear system influences the performance of classical iterative methods. In particular if, after a symmetric permutation, the blocks in the diagonal have more nonzeros, classical block methods have a faster asymptotic rate of convergence. In this paper, different ordering and partitioning algorithms for sparse matrices are presented. They are modifications of PABLO. In the new algorithms, in addition to the location of the nonzeros, the values of the entries are taken into account. The matrix resulting after the symmetric permutation has dense blocks along the diagonal, and small entries in the off-diagonal blocks. Parameters can be easily adjusted to obtain, for example, denser blocks, or blocks with elements of larger magnitude. In particular, when the matrices represent Markov chains, the permuted matrices are well suited for block iterative methods that find the corresponding probability distribution. Applications to three types of methods are explored: (1) Classical block methods, such as Block Gauss Seidel. (2) Preconditioned GMRES, where a block diagonal preconditioner is used. (3) Iterative aggregation method (also called aggregation/disaggregation) where the partition obtained from the ordering algorithm with certain parameters is used as an aggregation scheme. In all three cases, experiments are presented which illustrate the performance of the methods with the new orderings. The complexity of the new algorithms is linear in the number of nonzeros and the order of the matrix, and thus adding little computational effort to the overall solution.

Effects of Ordering Strategies and Programming Paradigms on Sparse Matrix Computations

Science.gov (United States)

Oliker, Leonid; Li, Xiaoye; Husbands, Parry; Biswas, Rupak; Biegel, Bryan (Technical Monitor)

2002-01-01

The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. For systems that are ill-conditioned, it is often necessary to use a preconditioning technique. In this paper, we investigate the effects of various ordering and partitioning strategies on the performance of parallel CG and ILU(O) preconditioned CG (PCG) using different programming paradigms and architectures. Results show that for this class of applications: ordering significantly improves overall performance on both distributed and distributed shared-memory systems, that cache reuse may be more important than reducing communication, that it is possible to achieve message-passing performance using shared-memory constructs through careful data ordering and distribution, and that a hybrid MPI+OpenMP paradigm increases programming complexity with little performance gains. A implementation of CG on the Cray MTA does not require special ordering or partitioning to obtain high efficiency and scalability, giving it a distinct advantage for adaptive applications; however, it shows limited scalability for PCG due to a lack of thread level parallelism.

Discrete Sparse Coding.

Science.gov (United States)

Exarchakis, Georgios; Lücke, Jörg

2017-11-01

Sparse coding algorithms with continuous latent variables have been the subject of a large number of studies. However, discrete latent spaces for sparse coding have been largely ignored. In this work, we study sparse coding with latents described by discrete instead of continuous prior distributions. We consider the general case in which the latents (while being sparse) can take on any value of a finite set of possible values and in which we learn the prior probability of any value from data. This approach can be applied to any data generated by discrete causes, and it can be applied as an approximation of continuous causes. As the prior probabilities are learned, the approach then allows for estimating the prior shape without assuming specific functional forms. To efficiently train the parameters of our probabilistic generative model, we apply a truncated expectation-maximization approach (expectation truncation) that we modify to work with a general discrete prior. We evaluate the performance of the algorithm by applying it to a variety of tasks: (1) we use artificial data to verify that the algorithm can recover the generating parameters from a random initialization, (2) use image patches of natural images and discuss the role of the prior for the extraction of image components, (3) use extracellular recordings of neurons to present a novel method of analysis for spiking neurons that includes an intuitive discretization strategy, and (4) apply the algorithm on the task of encoding audio waveforms of human speech. The diverse set of numerical experiments presented in this letter suggests that discrete sparse coding algorithms can scale efficiently to work with realistic data sets and provide novel statistical quantities to describe the structure of the data.

The Use of Sparse Direct Solver in Vector Finite Element Modeling for Calculating Two Dimensional (2-D) Magnetotelluric Responses in Transverse Electric (TE) Mode

Science.gov (United States)

Yihaa Roodhiyah, Lisa’; Tjong, Tiffany; Nurhasan; Sutarno, D.

2018-04-01

The late research, linear matrices of vector finite element in two dimensional(2-D) magnetotelluric (MT) responses modeling was solved by non-sparse direct solver in TE mode. Nevertheless, there is some weakness which have to be improved especially accuracy in the low frequency (10-3 Hz-10-5 Hz) which is not achieved yet and high cost computation in dense mesh. In this work, the solver which is used is sparse direct solver instead of non-sparse direct solverto overcome the weaknesses of solving linear matrices of vector finite element metod using non-sparse direct solver. Sparse direct solver will be advantageous in solving linear matrices of vector finite element method because of the matrix properties which is symmetrical and sparse. The validation of sparse direct solver in solving linear matrices of vector finite element has been done for a homogen half-space model and vertical contact model by analytical solution. Thevalidation result of sparse direct solver in solving linear matrices of vector finite element shows that sparse direct solver is more stable than non-sparse direct solver in computing linear problem of vector finite element method especially in low frequency. In the end, the accuracy of 2D MT responses modelling in low frequency (10-3 Hz-10-5 Hz) has been reached out under the efficient allocation memory of array and less computational time consuming.

Low Complexity Submatrix Divided MMSE Sparse-SQRD Detection for MIMO-OFDM with ESPAR Antenna Receiver

Directory of Open Access Journals (Sweden)

Diego Javier Reinoso Chisaguano

2013-01-01

Full Text Available Multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM with an electronically steerable passive array radiator (ESPAR antenna receiver can improve the bit error rate performance and obtains additional diversity gain without increasing the number of Radio Frequency (RF front-end circuits. However, due to the large size of the channel matrix, the computational cost required for the detection process using Vertical-Bell Laboratories Layered Space-Time (V-BLAST detection is too high to be implemented. Using the minimum mean square error sparse-sorted QR decomposition (MMSE sparse-SQRD algorithm for the detection process the average computational cost can be considerably reduced but is still higher compared with a conventional MIMOOFDM system without ESPAR antenna receiver. In this paper, we propose to use a low complexity submatrix divided MMSE sparse-SQRD algorithm for the detection process of MIMOOFDM with ESPAR antenna receiver. The computational cost analysis and simulation results show that on average the proposed scheme can further reduce the computational cost and achieve a complexity comparable to the conventional MIMO-OFDM detection schemes.

Solving Sparse Polynomial Optimization Problems with Chordal Structure Using the Sparse, Bounded-Degree Sum-of-Squares Hierarchy

NARCIS (Netherlands)

Marandi, Ahmadreza; de Klerk, Etienne; Dahl, Joachim

The sparse bounded degree sum-of-squares (sparse-BSOS) hierarchy of Weisser, Lasserre and Toh [arXiv:1607.01151,2016] constructs a sequence of lower bounds for a sparse polynomial optimization problem. Under some assumptions, it is proven by the authors that the sequence converges to the optimal

Data fusion in metabolomics using coupled matrix and tensor factorizations

DEFF Research Database (Denmark)

Evrim, Acar Ataman; Bro, Rasmus; Smilde, Age Klaas

2015-01-01

of heterogeneous (i.e., in the form of higher order tensors and matrices) data sets with shared/unshared factors. In order to jointly analyze such heterogeneous data sets, we formulate data fusion as a coupled matrix and tensor factorization (CMTF) problem, which has already proved useful in many data mining...

Reduction of Under-Determined Linear Systems by Sparce Block Matrix Technique

DEFF Research Database (Denmark)

Tarp-Johansen, Niels Jacob; Poulsen, Peter Noe; Damkilde, Lars

1996-01-01

numerical stability of the aforementioned reduction. Moreover the coefficient matrix for the equilibrium equations is typically very sparse. The objective is to deal efficiently with the full pivoting reduction of sparse rectangular matrices using a dynamic storage scheme based on the block matrix concept.......Under-determined linear equation systems occur in different engineering applications. In structural engineering they typically appear when applying the force method. As an example one could mention limit load analysis based on The Lower Bound Theorem. In this application there is a set of under......-determined equilibrium equation restrictions in an LP-problem. A significant reduction of computer time spent on solving the LP-problem is achieved if the equilib rium equations are reduced before going into the optimization procedure. Experience has shown that for some structures one must apply full pivoting to ensure...

High performance matrix inversion based on LU factorization for multicore architectures

KAUST Repository

Dongarra, Jack

2011-01-01

The goal of this paper is to present an efficient implementation of an explicit matrix inversion of general square matrices on multicore computer architecture. The inversion procedure is split into four steps: 1) computing the LU factorization, 2) inverting the upper triangular U factor, 3) solving a linear system, whose solution yields inverse of the original matrix and 4) applying backward column pivoting on the inverted matrix. Using a tile data layout, which represents the matrix in the system memory with an optimized cache-aware format, the computation of the four steps is decomposed into computational tasks. A directed acyclic graph is generated on the fly which represents the program data flow. Its nodes represent tasks and edges the data dependencies between them. Previous implementations of matrix inversions, available in the state-of-the-art numerical libraries, are suffer from unnecessary synchronization points, which are non-existent in our implementation in order to fully exploit the parallelism of the underlying hardware. Our algorithmic approach allows to remove these bottlenecks and to execute the tasks with loose synchronization. A runtime environment system called QUARK is necessary to dynamically schedule our numerical kernels on the available processing units. The reported results from our LU-based matrix inversion implementation significantly outperform the state-of-the-art numerical libraries such as LAPACK (5x), MKL (5x) and ScaLAPACK (2.5x) on a contemporary AMD platform with four sockets and the total of 48 cores for a matrix of size 24000. A power consumption analysis shows that our high performance implementation is also energy efficient and substantially consumes less power than its competitors. © 2011 ACM.

Extracellular matrix and growth factor engineering for controlled angiogenesis in regenerative medicine

Directory of Open Access Journals (Sweden)

Mikaël M Martino

2015-04-01

Full Text Available Blood vessel growth plays a key role in regenerative medicine, both to restore blood supply to ischemic tissues and to ensure rapid vascularization of clinical-size tissue-engineered grafts. For example, vascular endothelial growth factor (VEGF is the master regulator of physiological blood vessel growth and is one of the main molecular targets of therapeutic angiogenesis approaches. However, angiogenesis is a complex process and there is a need to develop rational therapeutic strategies based on a firm understanding of basic vascular biology principles, as evidenced by the disappointing results of initial clinical trials of angiogenic factor delivery. In particular, the spatial localization of angiogenic signals in the extracellular matrix is crucial to ensure the proper assembly and maturation of new vascular structures. Here we discuss the therapeutic implications of matrix interactions of angiogenic factors, with a special emphasis on VEGF, as well as provide an overview of current approaches, based on protein and biomaterial engineering that mimic the regulatory functions of extracellular matrix to optimize the signaling microenvironment of vascular growth factors.

Angiogenic Type I Collagen Extracellular Matrix Integrated with Recombinant Bacteriophages Displaying Vascular Endothelial Growth Factors.

Science.gov (United States)

Yoon, Junghyo; Korkmaz Zirpel, Nuriye; Park, Hyun-Ji; Han, Sewoon; Hwang, Kyung Hoon; Shin, Jisoo; Cho, Seung-Woo; Nam, Chang-Hoon; Chung, Seok

2016-01-21

Here, a growth-factor-integrated natural extracellular matrix of type I collagen is presented that induces angiogenesis. The developed matrix adapts type I collagen nanofibers integrated with synthetic colloidal particles of recombinant bacteriophages that display vascular endothelial growth factor (VEGF). The integration is achieved during or after gelation of the type I collagen and the matrix enables spatial delivery of VEGF into a desired region. Endothelial cells that contact the VEGF are found to invade into the matrix to form tube-like structures both in vitro and in vivo, proving the angiogenic potential of the matrix. © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Doubly sparse factor models for unifying feature transformation and feature selection

International Nuclear Information System (INIS)

Katahira, Kentaro; Okanoya, Kazuo; Okada, Masato; Matsumoto, Narihisa; Sugase-Miyamoto, Yasuko

2010-01-01

A number of unsupervised learning methods for high-dimensional data are largely divided into two groups based on their procedures, i.e., (1) feature selection, which discards irrelevant dimensions of the data, and (2) feature transformation, which constructs new variables by transforming and mixing over all dimensions. We propose a method that both selects and transforms features in a common Bayesian inference procedure. Our method imposes a doubly automatic relevance determination (ARD) prior on the factor loading matrix. We propose a variational Bayesian inference for our model and demonstrate the performance of our method on both synthetic and real data.

Doubly sparse factor models for unifying feature transformation and feature selection

Energy Technology Data Exchange (ETDEWEB)

Katahira, Kentaro; Okanoya, Kazuo; Okada, Masato [ERATO, Okanoya Emotional Information Project, Japan Science Technology Agency, Saitama (Japan); Matsumoto, Narihisa; Sugase-Miyamoto, Yasuko, E-mail: okada@k.u-tokyo.ac.j [Human Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Ibaraki (Japan)

2010-06-01

A number of unsupervised learning methods for high-dimensional data are largely divided into two groups based on their procedures, i.e., (1) feature selection, which discards irrelevant dimensions of the data, and (2) feature transformation, which constructs new variables by transforming and mixing over all dimensions. We propose a method that both selects and transforms features in a common Bayesian inference procedure. Our method imposes a doubly automatic relevance determination (ARD) prior on the factor loading matrix. We propose a variational Bayesian inference for our model and demonstrate the performance of our method on both synthetic and real data.

Comparison of two matrix data structures for advanced CSM testbed applications

Science.gov (United States)

Regelbrugge, M. E.; Brogan, F. A.; Nour-Omid, B.; Rankin, C. C.; Wright, M. A.

1989-01-01

The first section describes data storage schemes presently used by the Computational Structural Mechanics (CSM) testbed sparse matrix facilities and similar skyline (profile) matrix facilities. The second section contains a discussion of certain features required for the implementation of particular advanced CSM algorithms, and how these features might be incorporated into the data storage schemes described previously. The third section presents recommendations, based on the discussions of the prior sections, for directing future CSM testbed development to provide necessary matrix facilities for advanced algorithm implementation and use. The objective is to lend insight into the matrix structures discussed and to help explain the process of evaluating alternative matrix data structures and utilities for subsequent use in the CSM testbed.

Technique for information retrieval using enhanced latent semantic analysis generating rank approximation matrix by factorizing the weighted morpheme-by-document matrix

Science.gov (United States)

Chew, Peter A; Bader, Brett W

2012-10-16

A technique for information retrieval includes parsing a corpus to identify a number of wordform instances within each document of the corpus. A weighted morpheme-by-document matrix is generated based at least in part on the number of wordform instances within each document of the corpus and based at least in part on a weighting function. The weighted morpheme-by-document matrix separately enumerates instances of stems and affixes. Additionally or alternatively, a term-by-term alignment matrix may be generated based at least in part on the number of wordform instances within each document of the corpus. At least one lower rank approximation matrix is generated by factorizing the weighted morpheme-by-document matrix and/or the term-by-term alignment matrix.

Bayesian Inference Methods for Sparse Channel Estimation

DEFF Research Database (Denmark)

Pedersen, Niels Lovmand

2013-01-01

This thesis deals with sparse Bayesian learning (SBL) with application to radio channel estimation. As opposed to the classical approach for sparse signal representation, we focus on the problem of inferring complex signals. Our investigations within SBL constitute the basis for the development...... of Bayesian inference algorithms for sparse channel estimation. Sparse inference methods aim at finding the sparse representation of a signal given in some overcomplete dictionary of basis vectors. Within this context, one of our main contributions to the field of SBL is a hierarchical representation...... analysis of the complex prior representation, where we show that the ability to induce sparse estimates of a given prior heavily depends on the inference method used and, interestingly, whether real or complex variables are inferred. We also show that the Bayesian estimators derived from the proposed...

An NoC Traffic Compiler for Efficient FPGA Implementation of Sparse Graph-Oriented Workloads

Directory of Open Access Journals (Sweden)

Nachiket Kapre

2011-01-01

synchronization to optimize our workloads for large networks up to 2025 parallel elements for BSP model and 25 parallel elements for Token Dataflow. This allows us to demonstrate speedups between 1.2× and 22× (3.5× mean, area reductions (number of Processing Elements between 3× and 15× (9× mean and dynamic energy savings between 2× and 3.5× (2.7× mean over a range of real-world graph applications in the BSP compute model. We deliver speedups of 0.5–13× (geomean 3.6× for Sparse Direct Matrix Solve (Token Dataflow compute model applied to a range of sparse matrices when using a high-quality placement algorithm. We expect such traffic optimization tools and techniques to become an essential part of the NoC application-mapping flow.

When sparse coding meets ranking: a joint framework for learning sparse codes and ranking scores

KAUST Repository

Wang, Jim Jing-Yan; Cui, Xuefeng; Yu, Ge; Guo, Lili; Gao, Xin

2017-01-01

Sparse coding, which represents a data point as a sparse reconstruction code with regard to a dictionary, has been a popular data representation method. Meanwhile, in database retrieval problems, learning the ranking scores from data points plays

Compressed sensing for energy-efficient wireless telemonitoring of noninvasive fetal ECG via block sparse Bayesian learning.

Science.gov (United States)

Zhang, Zhilin; Jung, Tzyy-Ping; Makeig, Scott; Rao, Bhaskar D

2013-02-01

Fetal ECG (FECG) telemonitoring is an important branch in telemedicine. The design of a telemonitoring system via a wireless body area network with low energy consumption for ambulatory use is highly desirable. As an emerging technique, compressed sensing (CS) shows great promise in compressing/reconstructing data with low energy consumption. However, due to some specific characteristics of raw FECG recordings such as nonsparsity and strong noise contamination, current CS algorithms generally fail in this application. This paper proposes to use the block sparse Bayesian learning framework to compress/reconstruct nonsparse raw FECG recordings. Experimental results show that the framework can reconstruct the raw recordings with high quality. Especially, the reconstruction does not destroy the interdependence relation among the multichannel recordings. This ensures that the independent component analysis decomposition of the reconstructed recordings has high fidelity. Furthermore, the framework allows the use of a sparse binary sensing matrix with much fewer nonzero entries to compress recordings. Particularly, each column of the matrix can contain only two nonzero entries. This shows that the framework, compared to other algorithms such as current CS algorithms and wavelet algorithms, can greatly reduce code execution in CPU in the data compression stage.

Space Vector Modulation for an Indirect Matrix Converter with Improved Input Power Factor

Directory of Open Access Journals (Sweden)

Nguyen Dinh Tuyen

2017-04-01

Full Text Available Pulse width modulation strategies have been developed for indirect matrix converters (IMCs in order to improve their performance. In indirect matrix converters, the LC input filter is used to remove input current harmonics and electromagnetic interference problems. Unfortunately, due to the existence of the input filter, the input power factor is diminished, especially during operation at low voltage outputs. In this paper, a new space vector modulation (SVM is proposed to compensate for the input power factor of the indirect matrix converter. Both computer simulation and experimental studies through hardware implementation were performed to verify the effectiveness of the proposed modulation strategy.

Augmenting matrix factorization technique with the combination of tags and genres

Science.gov (United States)

Ma, Tinghuai; Suo, Xiafei; Zhou, Jinjuan; Tang, Meili; Guan, Donghai; Tian, Yuan; Al-Dhelaan, Abdullah; Al-Rodhaan, Mznah

2016-11-01

Recommender systems play an important role in our daily life and are becoming popular tools for users to find what they are really interested in. Matrix factorization methods, which are popular recommendation methods, have gained high attention these years. With the rapid growth of the Internet, lots of information has been created, like social network information, tags and so on. Along with these, a few matrix factorization approaches have been proposed which incorporate the personalized information of users or items. However, except for ratings, most of the matrix factorization models have utilized only one kind of information to understand users' interests. Considering the sparsity of information, in this paper, we try to investigate the combination of different information, like tags and genres, to reveal users' interests accurately. With regard to the generalization of genres, a constraint is added when genres are utilized to find users' similar ;soulmates;. In addition, item regularizer is also considered based on latent semantic indexing (LSI) method with the item tags. Our experiments are conducted on two real datasets: Movielens dataset and Douban dataset. The experimental results demonstrate that the combination of tags and genres is really helpful to reveal users' interests.

Improved Sparse Channel Estimation for Cooperative Communication Systems

Directory of Open Access Journals (Sweden)

Guan Gui

2012-01-01

Full Text Available Accurate channel state information (CSI is necessary at receiver for coherent detection in amplify-and-forward (AF cooperative communication systems. To estimate the channel, traditional methods, that is, least squares (LS and least absolute shrinkage and selection operator (LASSO, are based on assumptions of either dense channel or global sparse channel. However, LS-based linear method neglects the inherent sparse structure information while LASSO-based sparse channel method cannot take full advantage of the prior information. Based on the partial sparse assumption of the cooperative channel model, we propose an improved channel estimation method with partial sparse constraint. At first, by using sparse decomposition theory, channel estimation is formulated as a compressive sensing problem. Secondly, the cooperative channel is reconstructed by LASSO with partial sparse constraint. Finally, numerical simulations are carried out to confirm the superiority of proposed methods over global sparse channel estimation methods.

HPC-NMF: A High-Performance Parallel Algorithm for Nonnegative Matrix Factorization

Energy Technology Data Exchange (ETDEWEB)

2016-08-22

NMF is a useful tool for many applications in different domains such as topic modeling in text mining, background separation in video analysis, and community detection in social networks. Despite its popularity in the data mining community, there is a lack of efficient distributed algorithms to solve the problem for big data sets. We propose a high-performance distributed-memory parallel algorithm that computes the factorization by iteratively solving alternating non-negative least squares (NLS) subproblems for $\\WW$ and $\\HH$. It maintains the data and factor matrices in memory (distributed across processors), uses MPI for interprocessor communication, and, in the dense case, provably minimizes communication costs (under mild assumptions). As opposed to previous implementation, our algorithm is also flexible: It performs well for both dense and sparse matrices, and allows the user to choose any one of the multiple algorithms for solving the updates to low rank factors $\\WW$ and $\\HH$ within the alternating iterations.

Sparse Image Reconstruction in Computed Tomography

DEFF Research Database (Denmark)

Jørgensen, Jakob Sauer

In recent years, increased focus on the potentially harmful effects of x-ray computed tomography (CT) scans, such as radiation-induced cancer, has motivated research on new low-dose imaging techniques. Sparse image reconstruction methods, as studied for instance in the field of compressed sensing...... applications. This thesis takes a systematic approach toward establishing quantitative understanding of conditions for sparse reconstruction to work well in CT. A general framework for analyzing sparse reconstruction methods in CT is introduced and two sets of computational tools are proposed: 1...... contributions to a general set of computational characterization tools. Thus, the thesis contributions help advance sparse reconstruction methods toward routine use in...

Sparse Regression by Projection and Sparse Discriminant Analysis

KAUST Repository

Qi, Xin; Luo, Ruiyan; Carroll, Raymond J.; Zhao, Hongyu

2015-01-01

predictions. We introduce a new framework, regression by projection, and its sparse version to analyze high-dimensional data. The unique nature of this framework is that the directions of the regression coefficients are inferred first, and the lengths

Minimally invasive esthetic ridge preservation with growth-factor enhanced bone matrix.

Science.gov (United States)

Nevins, Marc L; Said, Sherif

2017-12-28

Extraction socket preservation procedures are critical to successful esthetic implant therapy. Conventional surgical approaches are technique sensitive and often result in alteration of the soft tissue architecture, which then requires additional corrective surgical procedures. This case series report presents the ability of flapless surgical techniques combined with a growth factor-enhanced bone matrix to provide esthetic ridge preservation at the time of extraction for compromised sockets. When considering esthetic dental implant therapy, preservation, or further enhancement of the available tissue support at the time of tooth extraction may provide an improved esthetic outcome with reduced postoperative sequelae and decreased treatment duration. Advances in minimally invasive surgical techniques combined with recombinant growth factor technology offer an alternative for bone reconstruction while maintaining the gingival architecture for enhanced esthetic outcome. The combination of freeze-dried bone allograft (FDBA) and rhPDGF-BB (platelet-derived growth factor-BB) provides a growth-factor enhanced matrix to induce bone and soft tissue healing. The use of a growth-factor enhanced matrix is an option for minimally invasive ridge preservation procedures for sites with advanced bone loss. Further studies including randomized clinical trials are needed to better understand the extent and limits of these procedures. The use of minimally invasive techniques with growth factors for esthetic ridge preservation reduces patient morbidity associated with more invasive approaches and increases the predictability for enhanced patient outcomes. By reducing the need for autogenous bone grafts the use of this technology is favorable for patient acceptance and ease of treatment process for esthetic dental implant therapy. © 2017 Wiley Periodicals, Inc.

An efficient optical architecture for sparsely connected neural networks

Science.gov (United States)

Hine, Butler P., III; Downie, John D.; Reid, Max B.

1990-01-01

An architecture for general-purpose optical neural network processor is presented in which the interconnections and weights are formed by directing coherent beams holographically, thereby making use of the space-bandwidth products of the recording medium for sparsely interconnected networks more efficiently that the commonly used vector-matrix multiplier, since all of the hologram area is in use. An investigation is made of the use of computer-generated holograms recorded on such updatable media as thermoplastic materials, in order to define the interconnections and weights of a neural network processor; attention is given to limits on interconnection densities, diffraction efficiencies, and weighing accuracies possible with such an updatable thin film holographic device.

Spectrum recovery method based on sparse representation for segmented multi-Gaussian model

Science.gov (United States)

Teng, Yidan; Zhang, Ye; Ti, Chunli; Su, Nan

2016-09-01

Hyperspectral images can realize crackajack features discriminability for supplying diagnostic characteristics with high spectral resolution. However, various degradations may generate negative influence on the spectral information, including water absorption, bands-continuous noise. On the other hand, the huge data volume and strong redundancy among spectrums produced intense demand on compressing HSIs in spectral dimension, which also leads to the loss of spectral information. The reconstruction of spectral diagnostic characteristics has irreplaceable significance for the subsequent application of HSIs. This paper introduces a spectrum restoration method for HSIs making use of segmented multi-Gaussian model (SMGM) and sparse representation. A SMGM is established to indicating the unsymmetrical spectral absorption and reflection characteristics, meanwhile, its rationality and sparse property are discussed. With the application of compressed sensing (CS) theory, we implement sparse representation to the SMGM. Then, the degraded and compressed HSIs can be reconstructed utilizing the uninjured or key bands. Finally, we take low rank matrix recovery (LRMR) algorithm for post processing to restore the spatial details. The proposed method was tested on the spectral data captured on the ground with artificial water absorption condition and an AVIRIS-HSI data set. The experimental results in terms of qualitative and quantitative assessments demonstrate that the effectiveness on recovering the spectral information from both degradations and loss compression. The spectral diagnostic characteristics and the spatial geometry feature are well preserved.

Sparse Linear Identifiable Multivariate Modeling

DEFF Research Database (Denmark)

Henao, Ricardo; Winther, Ole

2011-01-01

and bench-marked on artificial and real biological data sets. SLIM is closest in spirit to LiNGAM (Shimizu et al., 2006), but differs substantially in inference, Bayesian network structure learning and model comparison. Experimentally, SLIM performs equally well or better than LiNGAM with comparable......In this paper we consider sparse and identifiable linear latent variable (factor) and linear Bayesian network models for parsimonious analysis of multivariate data. We propose a computationally efficient method for joint parameter and model inference, and model comparison. It consists of a fully...

A Non-static Data Layout Enhancing Parallelism and Vectorization in Sparse Grid Algorithms

KAUST Repository

Buse, Gerrit

2012-06-01

The name sparse grids denotes a highly space-efficient, grid-based numerical technique to approximate high-dimensional functions. Although employed in a broad spectrum of applications from different fields, there have only been few tries to use it in real time visualization (e.g. [1]), due to complex data structures and long algorithm runtime. In this work we present a novel approach inspired by principles of I/0-efficient algorithms. Locally applied coefficient permutations lead to improved cache performance and facilitate the use of vector registers for our sparse grid benchmark problem hierarchization. Based on the compact data structure proposed for regular sparse grids in [2], we developed a new algorithm that outperforms existing implementations on modern multi-core systems by a factor of 37 for a grid size of 127 million points. For larger problems the speedup is even increasing, and with execution times below 1 s, sparse grids are well-suited for visualization applications. Furthermore, we point out how a broad class of sparse grid algorithms can benefit from our approach. © 2012 IEEE.

JiTTree: A Just-in-Time Compiled Sparse GPU Volume Data Structure

KAUST Repository

Labschutz, Matthias

2015-08-12

Sparse volume data structures enable the efficient representation of large but sparse volumes in GPU memory for computation and visualization. However, the choice of a specific data structure for a given data set depends on several factors, such as the memory budget, the sparsity of the data, and data access patterns. In general, there is no single optimal sparse data structure, but a set of several candidates with individual strengths and drawbacks. One solution to this problem are hybrid data structures which locally adapt themselves to the sparsity. However, they typically suffer from increased traversal overhead which limits their utility in many applications. This paper presents JiTTree, a novel sparse hybrid volume data structure that uses just-in-time compilation to overcome these problems. By combining multiple sparse data structures and reducing traversal overhead we leverage their individual advantages. We demonstrate that hybrid data structures adapt well to a large range of data sets. They are especially superior to other sparse data structures for data sets that locally vary in sparsity. Possible optimization criteria are memory, performance and a combination thereof. Through just-in-time (JIT) compilation, JiTTree reduces the traversal overhead of the resulting optimal data structure. As a result, our hybrid volume data structure enables efficient computations on the GPU, while being superior in terms of memory usage when compared to non-hybrid data structures.

JiTTree: A Just-in-Time Compiled Sparse GPU Volume Data Structure

KAUST Repository

Labschutz, Matthias; Bruckner, Stefan; Groller, M. Eduard; Hadwiger, Markus; Rautek, Peter

2015-01-01

Sparse volume data structures enable the efficient representation of large but sparse volumes in GPU memory for computation and visualization. However, the choice of a specific data structure for a given data set depends on several factors, such as the memory budget, the sparsity of the data, and data access patterns. In general, there is no single optimal sparse data structure, but a set of several candidates with individual strengths and drawbacks. One solution to this problem are hybrid data structures which locally adapt themselves to the sparsity. However, they typically suffer from increased traversal overhead which limits their utility in many applications. This paper presents JiTTree, a novel sparse hybrid volume data structure that uses just-in-time compilation to overcome these problems. By combining multiple sparse data structures and reducing traversal overhead we leverage their individual advantages. We demonstrate that hybrid data structures adapt well to a large range of data sets. They are especially superior to other sparse data structures for data sets that locally vary in sparsity. Possible optimization criteria are memory, performance and a combination thereof. Through just-in-time (JIT) compilation, JiTTree reduces the traversal overhead of the resulting optimal data structure. As a result, our hybrid volume data structure enables efficient computations on the GPU, while being superior in terms of memory usage when compared to non-hybrid data structures.

JiTTree: A Just-in-Time Compiled Sparse GPU Volume Data Structure.

Science.gov (United States)

Labschütz, Matthias; Bruckner, Stefan; Gröller, M Eduard; Hadwiger, Markus; Rautek, Peter

2016-01-01

Sparse volume data structures enable the efficient representation of large but sparse volumes in GPU memory for computation and visualization. However, the choice of a specific data structure for a given data set depends on several factors, such as the memory budget, the sparsity of the data, and data access patterns. In general, there is no single optimal sparse data structure, but a set of several candidates with individual strengths and drawbacks. One solution to this problem are hybrid data structures which locally adapt themselves to the sparsity. However, they typically suffer from increased traversal overhead which limits their utility in many applications. This paper presents JiTTree, a novel sparse hybrid volume data structure that uses just-in-time compilation to overcome these problems. By combining multiple sparse data structures and reducing traversal overhead we leverage their individual advantages. We demonstrate that hybrid data structures adapt well to a large range of data sets. They are especially superior to other sparse data structures for data sets that locally vary in sparsity. Possible optimization criteria are memory, performance and a combination thereof. Through just-in-time (JIT) compilation, JiTTree reduces the traversal overhead of the resulting optimal data structure. As a result, our hybrid volume data structure enables efficient computations on the GPU, while being superior in terms of memory usage when compared to non-hybrid data structures.

Sparse decompositions in 'incoherent' dictionaries

DEFF Research Database (Denmark)

Gribonval, R.; Nielsen, Morten

2003-01-01

a unique sparse representation in such a dictionary. In particular, it is proved that the result of Donoho and Huo, concerning the replacement of a combinatorial optimization problem with a linear programming problem when searching for sparse representations, has an analog for dictionaries that may...

Face recognition based on two-dimensional discriminant sparse preserving projection

Science.gov (United States)

Zhang, Dawei; Zhu, Shanan

2018-04-01

In this paper, a supervised dimensionality reduction algorithm named two-dimensional discriminant sparse preserving projection (2DDSPP) is proposed for face recognition. In order to accurately model manifold structure of data, 2DDSPP constructs within-class affinity graph and between-class affinity graph by the constrained least squares (LS) and l1 norm minimization problem, respectively. Based on directly operating on image matrix, 2DDSPP integrates graph embedding (GE) with Fisher criterion. The obtained projection subspace preserves within-class neighborhood geometry structure of samples, while keeping away samples from different classes. The experimental results on the PIE and AR face databases show that 2DDSPP can achieve better recognition performance.

An Elementary Proof of the Polynomial Matrix Spectral Factorization Theorem

OpenAIRE

Ephremidze, Lasha

2010-01-01

A very simple and short proof of the polynomial matrix spectral factorization theorem (on the unit circle as well as on the real line) is presented, which relies on elementary complex analysis and linear algebra.

Semi-Supervised Half-Quadratic Nonnegative Matrix Factorization for Face Recognition

KAUST Repository

Alghamdi, Masheal M.

2014-01-01

complications to the face recognition research. Many algorithms are devoted to solving the face recognition problem, among which the family of nonnegative matrix factorization (NMF) algorithms has been widely used as a compact data representation method

Data analysis in high-dimensional sparse spaces

DEFF Research Database (Denmark)

Clemmensen, Line Katrine Harder

classification techniques for high-dimensional problems are presented: Sparse discriminant analysis, sparse mixture discriminant analysis and orthogonality constrained support vector machines. The first two introduces sparseness to the well known linear and mixture discriminant analysis and thereby provide low...... are applied to classifications of fish species, ear canal impressions used in the hearing aid industry, microbiological fungi species, and various cancerous tissues and healthy tissues. In addition, novel applications of sparse regressions (also called the elastic net) to the medical, concrete, and food...

Orthogonal sparse linear discriminant analysis

Science.gov (United States)

Liu, Zhonghua; Liu, Gang; Pu, Jiexin; Wang, Xiaohong; Wang, Haijun

2018-03-01

Linear discriminant analysis (LDA) is a linear feature extraction approach, and it has received much attention. On the basis of LDA, researchers have done a lot of research work on it, and many variant versions of LDA were proposed. However, the inherent problem of LDA cannot be solved very well by the variant methods. The major disadvantages of the classical LDA are as follows. First, it is sensitive to outliers and noises. Second, only the global discriminant structure is preserved, while the local discriminant information is ignored. In this paper, we present a new orthogonal sparse linear discriminant analysis (OSLDA) algorithm. The k nearest neighbour graph is first constructed to preserve the locality discriminant information of sample points. Then, L2,1-norm constraint on the projection matrix is used to act as loss function, which can make the proposed method robust to outliers in data points. Extensive experiments have been performed on several standard public image databases, and the experiment results demonstrate the performance of the proposed OSLDA algorithm.

A sparse-grid isogeometric solver

KAUST Repository

Beck, Joakim; Sangalli, Giancarlo; Tamellini, Lorenzo

2018-01-01

Isogeometric Analysis (IGA) typically adopts tensor-product splines and NURBS as a basis for the approximation of the solution of PDEs. In this work, we investigate to which extent IGA solvers can benefit from the so-called sparse-grids construction in its combination technique form, which was first introduced in the early 90’s in the context of the approximation of high-dimensional PDEs.The tests that we report show that, in accordance to the literature, a sparse-grid construction can indeed be useful if the solution of the PDE at hand is sufficiently smooth. Sparse grids can also be useful in the case of non-smooth solutions when some a-priori knowledge on the location of the singularities of the solution can be exploited to devise suitable non-equispaced meshes. Finally, we remark that sparse grids can be seen as a simple way to parallelize pre-existing serial IGA solvers in a straightforward fashion, which can be beneficial in many practical situations.

A sparse-grid isogeometric solver

KAUST Repository

Beck, Joakim

2018-02-28

Isogeometric Analysis (IGA) typically adopts tensor-product splines and NURBS as a basis for the approximation of the solution of PDEs. In this work, we investigate to which extent IGA solvers can benefit from the so-called sparse-grids construction in its combination technique form, which was first introduced in the early 90’s in the context of the approximation of high-dimensional PDEs.The tests that we report show that, in accordance to the literature, a sparse-grid construction can indeed be useful if the solution of the PDE at hand is sufficiently smooth. Sparse grids can also be useful in the case of non-smooth solutions when some a-priori knowledge on the location of the singularities of the solution can be exploited to devise suitable non-equispaced meshes. Finally, we remark that sparse grids can be seen as a simple way to parallelize pre-existing serial IGA solvers in a straightforward fashion, which can be beneficial in many practical situations.

The impact of improved sparse linear solvers on industrial engineering applications

Energy Technology Data Exchange (ETDEWEB)

Heroux, M. [Cray Research, Inc., Eagan, MN (United States); Baddourah, M.; Poole, E.L.; Yang, Chao Wu

1996-12-31

There are usually many factors that ultimately determine the quality of computer simulation for engineering applications. Some of the most important are the quality of the analytical model and approximation scheme, the accuracy of the input data and the capability of the computing resources. However, in many engineering applications the characteristics of the sparse linear solver are the key factors in determining how complex a problem a given application code can solve. Therefore, the advent of a dramatically improved solver often brings with it dramatic improvements in our ability to do accurate and cost effective computer simulations. In this presentation we discuss the current status of sparse iterative and direct solvers in several key industrial CFD and structures codes, and show the impact that recent advances in linear solvers have made on both our ability to perform challenging simulations and the cost of those simulations. We also present some of the current challenges we have and the constraints we face in trying to improve these solvers. Finally, we discuss future requirements for sparse linear solvers on high performance architectures and try to indicate the opportunities that exist if we can develop even more improvements in linear solver capabilities.

Calabi-Yau structures on categories of matrix factorizations

Science.gov (United States)

Shklyarov, Dmytro

2017-09-01

Using tools of complex geometry, we construct explicit proper Calabi-Yau structures, that is, non-degenerate cyclic cocycles on differential graded categories of matrix factorizations of regular functions with isolated critical points. The formulas involve the Kapustin-Li trace and its higher corrections. From the physics perspective, our result yields explicit 'off-shell' models for categories of topological D-branes in B-twisted Landau-Ginzburg models.

A Current Control Approach for an Abnormal Grid Supplied Ultra Sparse Z-Source Matrix Converter with a Particle Swarm Optimization Proportional-Integral Induction Motor Drive Controller

Directory of Open Access Journals (Sweden)

Seyed Sina Sebtahmadi

2016-11-01

Full Text Available A rotational d-q current control scheme based on a Particle Swarm Optimization- Proportional-Integral (PSO-PI controller, is used to drive an induction motor (IM through an Ultra Sparse Z-source Matrix Converter (USZSMC. To minimize the overall size of the system, the lowest feasible values of Z-source elements are calculated by considering the both timing and aspects of the circuit. A meta-heuristic method is integrated to the control system in order to find optimal coefficient values in a single multimodal problem. Henceforth, the effect of all coefficients in minimizing the total harmonic distortion (THD and balancing the stator current are considered simultaneously. Through changing the reference point of magnitude or frequency, the modulation index can be automatically adjusted and respond to changes without heavy computational cost. The focus of this research is on a reliable and lightweight system with low computational resources. The proposed scheme is validated through both simulation and experimental results.

Metal matrix composites: History, status, factors and future

Science.gov (United States)

Cyriac, Ajith James

The history, status, and future of metal matrix composites are presented by evaluating the progression of available literature through time. The trends that existed and issues that still prevail are discussed and a prediction of the future for MMCs is presented. The factors that govern the performance of metal matrix composites are also discussed. In many developed countries and in several developing countries there exists continued interest in MMCs. Researchers tried numerous combinations of matrices and reinforcements since work strictly on MMCs began in the 1950s. This led to developments for aerospace and defense applications, but resultant commercial applications were limited. The introduction of ceramic whiskers as reinforcement and the development of 'in-situ' eutectics in the 1960s aided high temperature applications in aircraft engines. In the late 1970s the automobile industries started to take MMCs seriously. In the last 20 years, MMCs evolved from laboratories to a class of materials with numerous applications and commercial markets. After the collapse of the Berlin Wall, prevailing order in the world changed drastically. This effect was evident in the progression of metal matrix composites. The internet connected the world like never before and tremendous information was available for researchers around the world. Globalization and the internet resulted in the transformation of the world to a more level playing field, and this effect is evident in the nature and source of research on metal matrix composites happening around the world.

Joint Group Sparse PCA for Compressed Hyperspectral Imaging.

Science.gov (United States)

Khan, Zohaib; Shafait, Faisal; Mian, Ajmal

2015-12-01

A sparse principal component analysis (PCA) seeks a sparse linear combination of input features (variables), so that the derived features still explain most of the variations in the data. A group sparse PCA introduces structural constraints on the features in seeking such a linear combination. Collectively, the derived principal components may still require measuring all the input features. We present a joint group sparse PCA (JGSPCA) algorithm, which forces the basic coefficients corresponding to a group of features to be jointly sparse. Joint sparsity ensures that the complete basis involves only a sparse set of input features, whereas the group sparsity ensures that the structural integrity of the features is maximally preserved. We evaluate the JGSPCA algorithm on the problems of compressed hyperspectral imaging and face recognition. Compressed sensing results show that the proposed method consistently outperforms sparse PCA and group sparse PCA in reconstructing the hyperspectral scenes of natural and man-made objects. The efficacy of the proposed compressed sensing method is further demonstrated in band selection for face recognition.

Improvement of the Convergence of the Invariant Imbedding T-Matrix Method

Science.gov (United States)

Zhai, S.; Panetta, R. L.; Yang, P.

2017-12-01

The invariant imbedding T-matrix method (IITM) is based on an electromagnetic volume integral equation to compute the T-matrix of an arbitrary scattering particle. A free-space Green's function is chosen as the integral kernel and thus each source point is placed in an imaginary vacuum spherical shell extending from the center to that source point. The final T-matrix (of the largest circumscribing sphere) is obtained through an iterative relation that, layer by layer, computes the T-matrix from the particle center to the outermost shell. On each spherical shell surface, an integration of the product of the refractive index 𝜀(𝜃, 𝜑) and vector spherical harmonics must be performed, resulting in the so-called U-matrix, which directly leads to the T-matrix on the spherical surface. Our observations indicate that the matrix size and sparseness are determined by the particular refractive index function 𝜀(𝜃, 𝜑). If 𝜀(𝜃, 𝜑) is an analytic function on the surface, then the matrix elements resulting from the integration decay rapidly, leading to sparse matrix; if 𝜀(𝜃, 𝜑) is not (for example, contains jump discontinuities), then the matrix elements decay slowly, leading to a large dense matrix. The intersection between an irregular scatterer and each spherical shell can leave jump discontinuities in 𝜀(𝜃, 𝜑) distributed over the shell surface. The aforementioned feature is analogous to the Gibbs phenomenon appearing in the orthogonal expansion of non-smooth functions with Hermitian eigenfunctions (complex exponential, Legendre, Bessel,...) where poor convergence speed is a direct consequence of the slow decay rate of the expansion coefficients. Various methods have been developed to deal with this slow convergence in the presence of discontinuities. Among the different approaches the most practical one may be a spectral filter: a filter is applied on the

Calculation of the Cholesky factor directly from the stiffness matrix of the structural element

International Nuclear Information System (INIS)

Prates, C.L.M.; Soriano, H.L.

1978-01-01

The analysis of the structures of nuclear power plants requires the evaluation of the internal forces. This is attained by the solution of a system of equations. This solution takes most of the computing time and memory. One of the ways it can be achieved is based on the Cholesky factor. The structural matrix of the coeficients is transformed into an upper triangular matrix by the Cholesky decomposition. Cholesky factor can be obtained directly from the stiffness matrix of the structural element. The result can thus be obtained in a more precise and quick way. (Author)

Robust and Sparse Factor Modelling

DEFF Research Database (Denmark)

Croux, Christophe; Exterkate, Peter

Factor construction methods are widely used to summarize a large panel of variables by means of a relatively small number of representative factors. We propose a novel factor construction procedure that enjoys the properties of robustness to outliers and of sparsity; that is, having relatively few...... nonzero factor loadings. Compared to the traditional factor construction method, we find that this procedure leads to a favorable forecasting performance in the presence of outliers and to better interpretable factors. We investigate the performance of the method in a Monte Carlo experiment...

Distance descending ordering method: An O(n) algorithm for inverting the mass matrix in simulation of macromolecules with long branches

Science.gov (United States)

Xu, Xiankun; Li, Peiwen

2017-11-01

Fixman's work in 1974 and the follow-up studies have developed a method that can factorize the inverse of mass matrix into an arithmetic combination of three sparse matrices-one of them is positive definite and needs to be further factorized by using the Cholesky decomposition or similar methods. When the molecule subjected to study is of serial chain structure, this method can achieve O (n) time complexity. However, for molecules with long branches, Cholesky decomposition about the corresponding positive definite matrix will introduce massive fill-in due to its nonzero structure. Although there are several methods can be used to reduce the number of fill-in, none of them could strictly guarantee for zero fill-in for all molecules according to our test, and thus cannot obtain O (n) time complexity by using these traditional methods. In this paper we present a new method that can guarantee for no fill-in in doing the Cholesky decomposition, which was developed based on the correlations between the mass matrix and the geometrical structure of molecules. As a result, the inverting of mass matrix will remain the O (n) time complexity, no matter the molecule structure has long branches or not.

Non-negative matrix factorization by maximizing correntropy for cancer clustering

KAUST Repository

Wang, Jim Jing-Yan; Wang, Xiaolei; Gao, Xin

2013-01-01

Background: Non-negative matrix factorization (NMF) has been shown to be a powerful tool for clustering gene expression data, which are widely used to classify cancers. NMF aims to find two non-negative matrices whose product closely approximates the original matrix. Traditional NMF methods minimize either the l2 norm or the Kullback-Leibler distance between the product of the two matrices and the original matrix. Correntropy was recently shown to be an effective similarity measurement due to its stability to outliers or noise.Results: We propose a maximum correntropy criterion (MCC)-based NMF method (NMF-MCC) for gene expression data-based cancer clustering. Instead of minimizing the l2 norm or the Kullback-Leibler distance, NMF-MCC maximizes the correntropy between the product of the two matrices and the original matrix. The optimization problem can be solved by an expectation conditional maximization algorithm.Conclusions: Extensive experiments on six cancer benchmark sets demonstrate that the proposed method is significantly more accurate than the state-of-the-art methods in cancer clustering. 2013 Wang et al.; licensee BioMed Central Ltd.

Non-negative matrix factorization by maximizing correntropy for cancer clustering

KAUST Repository

Wang, Jim Jing-Yan

2013-03-24

Background: Non-negative matrix factorization (NMF) has been shown to be a powerful tool for clustering gene expression data, which are widely used to classify cancers. NMF aims to find two non-negative matrices whose product closely approximates the original matrix. Traditional NMF methods minimize either the l2 norm or the Kullback-Leibler distance between the product of the two matrices and the original matrix. Correntropy was recently shown to be an effective similarity measurement due to its stability to outliers or noise.Results: We propose a maximum correntropy criterion (MCC)-based NMF method (NMF-MCC) for gene expression data-based cancer clustering. Instead of minimizing the l2 norm or the Kullback-Leibler distance, NMF-MCC maximizes the correntropy between the product of the two matrices and the original matrix. The optimization problem can be solved by an expectation conditional maximization algorithm.Conclusions: Extensive experiments on six cancer benchmark sets demonstrate that the proposed method is significantly more accurate than the state-of-the-art methods in cancer clustering. 2013 Wang et al.; licensee BioMed Central Ltd.

Sparse approximation with bases

CERN Document Server

2015-01-01

This book systematically presents recent fundamental results on greedy approximation with respect to bases. Motivated by numerous applications, the last decade has seen great successes in studying nonlinear sparse approximation. Recent findings have established that greedy-type algorithms are suitable methods of nonlinear approximation in both sparse approximation with respect to bases and sparse approximation with respect to redundant systems. These insights, combined with some previous fundamental results, form the basis for constructing the theory of greedy approximation. Taking into account the theoretical and practical demand for this kind of theory, the book systematically elaborates a theoretical framework for greedy approximation and its applications.  The book addresses the needs of researchers working in numerical mathematics, harmonic analysis, and functional analysis. It quickly takes the reader from classical results to the latest frontier, but is written at the level of a graduate course and do...

Efficient convolutional sparse coding

Science.gov (United States)

Wohlberg, Brendt

2017-06-20

Computationally efficient algorithms may be applied for fast dictionary learning solving the convolutional sparse coding problem in the Fourier domain. More specifically, efficient convolutional sparse coding may be derived within an alternating direction method of multipliers (ADMM) framework that utilizes fast Fourier transforms (FFT) to solve the main linear system in the frequency domain. Such algorithms may enable a significant reduction in computational cost over conventional approaches by implementing a linear solver for the most critical and computationally expensive component of the conventional iterative algorithm. The theoretical computational cost of the algorithm may be reduced from O(M.sup.3N) to O(MN log N), where N is the dimensionality of the data and M is the number of elements in the dictionary. This significant improvement in efficiency may greatly increase the range of problems that can practically be addressed via convolutional sparse representations.

Hyperspectral Unmixing with Robust Collaborative Sparse Regression

Directory of Open Access Journals (Sweden)

Chang Li

2016-07-01

Full Text Available Recently, sparse unmixing (SU of hyperspectral data has received particular attention for analyzing remote sensing images. However, most SU methods are based on the commonly admitted linear mixing model (LMM, which ignores the possible nonlinear effects (i.e., nonlinearity. In this paper, we propose a new method named robust collaborative sparse regression (RCSR based on the robust LMM (rLMM for hyperspectral unmixing. The rLMM takes the nonlinearity into consideration, and the nonlinearity is merely treated as outlier, which has the underlying sparse property. The RCSR simultaneously takes the collaborative sparse property of the abundance and sparsely distributed additive property of the outlier into consideration, which can be formed as a robust joint sparse regression problem. The inexact augmented Lagrangian method (IALM is used to optimize the proposed RCSR. The qualitative and quantitative experiments on synthetic datasets and real hyperspectral images demonstrate that the proposed RCSR is efficient for solving the hyperspectral SU problem compared with the other four state-of-the-art algorithms.

All-at-once Optimization for Coupled Matrix and Tensor Factorizations

DEFF Research Database (Denmark)

Evrim, Acar Ataman; Kolda, Tamara G.; Dunlavy, Daniel M.

2011-01-01

.g., the person by person social network matrix or the restaurant by category matrix, and higher-order tensors, e.g., the "ratings" tensor of the form restaurant by meal by person. In this paper, we are particularly interested in fusing data sets with the goal of capturing their underlying latent structures. We...... formulate this problem as a coupled matrix and tensor factorization (CMTF) problem where heterogeneous data sets are modeled by fitting outer-product models to higher-order tensors and matrices in a coupled manner. Unlike traditional approaches solving this problem using alternating algorithms, we propose...... an all-at-once optimization approach called CMTF-OPT (CMTF-OPTimization), which is a gradient-based optimization approach for joint analysis of matrices and higher-order tensors. We also extend the algorithm to handle coupled incomplete data sets. Using numerical experiments, we demonstrate...

Multithreading for synchronization tolerance in matrix factorization

International Nuclear Information System (INIS)

Buttari, Alfredo; Dongarra, Jack; Husbands, Parry; Kurzak, Jakub; Yelick, Katherine

2007-01-01

Physical constraints such as power, leakage and pin bandwidth are currently driving the HPC industry to produce systems with unprecedented levels of concurrency. In these parallel systems, synchronization and memory operations are becoming considerably more expensive than before. In this work we study parallel matrix factorization codes and conclude that they need to be re-engineered to avoid unnecessary (and expensive) synchronization. We propose the use of multithreading combined with intelligent schedulers and implement representative algorithms in this style. Our results indicate that this strategy can significantly outperform traditional codes

Real-time cardiac magnetic resonance cine imaging with sparse sampling and iterative reconstruction for left-ventricular measures: Comparison with gold-standard segmented steady-state free precession.

Science.gov (United States)

Camargo, Gabriel C; Erthal, Fernanda; Sabioni, Leticia; Penna, Filipe; Strecker, Ralph; Schmidt, Michaela; Zenge, Michael O; Lima, Ronaldo de S L; Gottlieb, Ilan

2017-05-01

Segmented cine imaging with a steady-state free-precession sequence (Cine-SSFP) is currently the gold standard technique for measuring ventricular volumes and mass, but due to multi breath-hold (BH) requirements, it is prone to misalignment of consecutive slices, time consuming and dependent on respiratory capacity. Real-time cine avoids those limitations, but poor spatial and temporal resolution of conventional sequences has prevented its routine application. We sought to examine the accuracy and feasibility of a newly developed real-time sequence with aggressive under-sampling of k-space using sparse sampling and iterative reconstruction (Cine-RT). Stacks of short-axis cines were acquired covering both ventricles in a 1.5T system using gold standard Cine-SSFP and Cine-RT. Acquisition parameters for Cine-SSFP were: acquisition matrix of 224×196, temporal resolution of 39ms, retrospective gating, with an average of 8 heartbeats per slice and 1-2 slices/BH. For Cine-RT: acquisition matrix of 224×196, sparse sampling net acceleration factor of 11.3, temporal resolution of 41ms, prospective gating, real-time acquisition of 1 heart-beat/slice and all slices in one BH. LV contours were drawn at end diastole and systole to derive LV volumes and mass. Forty-one consecutive patients (15 male; 41±17years) in sinus rhythm were successfully included. All images from Cine-SSFP and Cine-RT were considered to have excellent quality. Cine-RT-derived LV volumes and mass were slightly underestimated but strongly correlated with gold standard Cine-SSFP. Inter- and intra-observer analysis presented similar results between both sequences. Cine-RT featuring sparse sampling and iterative reconstruction can achieve spatial and temporal resolution equivalent to Cine-SSFP, providing excellent image quality, with similar precision measurements and highly correlated and only slightly underestimated volume and mass values. Copyright © 2017 Elsevier Inc. All rights reserved.

Image fusion using sparse overcomplete feature dictionaries

Science.gov (United States)

Brumby, Steven P.; Bettencourt, Luis; Kenyon, Garrett T.; Chartrand, Rick; Wohlberg, Brendt

2015-10-06

Approaches for deciding what individuals in a population of visual system "neurons" are looking for using sparse overcomplete feature dictionaries are provided. A sparse overcomplete feature dictionary may be learned for an image dataset and a local sparse representation of the image dataset may be built using the learned feature dictionary. A local maximum pooling operation may be applied on the local sparse representation to produce a translation-tolerant representation of the image dataset. An object may then be classified and/or clustered within the translation-tolerant representation of the image dataset using a supervised classification algorithm and/or an unsupervised clustering algorithm.

Large-Scale Distributed Bayesian Matrix Factorization using Stochastic Gradient MCMC

NARCIS (Netherlands)

Ahn, S.; Korattikara, A.; Liu, N.; Rajan, S.; Welling, M.

2015-01-01

Despite having various attractive qualities such as high prediction accuracy and the ability to quantify uncertainty and avoid ovrfitting, Bayesian Matrix Factorization has not been widely adopted because of the prohibitive cost of inference. In this paper, we propose a scalable distributed Bayesian

Multiple Kernel Sparse Representation based Orthogonal Discriminative Projection and Its Cost-Sensitive Extension.

Science.gov (United States)

Zhang, Guoqing; Sun, Huaijiang; Xia, Guiyu; Sun, Quansen

2016-07-07

Sparse representation based classification (SRC) has been developed and shown great potential for real-world application. Based on SRC, Yang et al. [10] devised a SRC steered discriminative projection (SRC-DP) method. However, as a linear algorithm, SRC-DP cannot handle the data with highly nonlinear distribution. Kernel sparse representation-based classifier (KSRC) is a non-linear extension of SRC and can remedy the drawback of SRC. KSRC requires the use of a predetermined kernel function and selection of the kernel function and its parameters is difficult. Recently, multiple kernel learning for SRC (MKL-SRC) [22] has been proposed to learn a kernel from a set of base kernels. However, MKL-SRC only considers the within-class reconstruction residual while ignoring the between-class relationship, when learning the kernel weights. In this paper, we propose a novel multiple kernel sparse representation-based classifier (MKSRC), and then we use it as a criterion to design a multiple kernel sparse representation based orthogonal discriminative projection method (MK-SR-ODP). The proposed algorithm aims at learning a projection matrix and a corresponding kernel from the given base kernels such that in the low dimension subspace the between-class reconstruction residual is maximized and the within-class reconstruction residual is minimized. Furthermore, to achieve a minimum overall loss by performing recognition in the learned low-dimensional subspace, we introduce cost information into the dimensionality reduction method. The solutions for the proposed method can be efficiently found based on trace ratio optimization method [33]. Extensive experimental results demonstrate the superiority of the proposed algorithm when compared with the state-of-the-art methods.

An integrating factor matrix method to find first integrals

International Nuclear Information System (INIS)

Saputra, K V I; Quispel, G R W; Van Veen, L

2010-01-01

In this paper we develop an integrating factor matrix method to derive conditions for the existence of first integrals. We use this novel method to obtain first integrals, along with the conditions for their existence, for two- and three-dimensional Lotka-Volterra systems with constant terms. The results are compared to previous results obtained by other methods.

Sparse direct solver for large finite element problems based on the minimum degree algorithm

Czech Academy of Sciences Publication Activity Database

Pařík, Petr; Plešek, Jiří

2017-01-01

Roč. 113, November (2017), s. 2-6 ISSN 0965-9978 R&D Projects: GA ČR(CZ) GA15-20666S; GA MŠk(CZ) EF15_003/0000493 Institutional support: RVO:61388998 Keywords : sparse direct solution * finite element method * large sparse Linear systems Subject RIV: JR - Other Machinery OBOR OECD: Mechanical engineering Impact factor: 3.000, year: 2016 https://www.sciencedirect.com/science/article/pii/S0965997817302582

Anonymising the Sparse Dataset: A New Privacy Preservation Approach while Predicting Diseases

Directory of Open Access Journals (Sweden)

V. Shyamala Susan

2016-09-01

Full Text Available Data mining techniques analyze the medical dataset with the intention of enhancing patient’s health and privacy. Most of the existing techniques are properly suited for low dimensional medical dataset. The proposed methodology designs a model for the representation of sparse high dimensional medical dataset with the attitude of protecting the patient’s privacy from an adversary and additionally to predict the disease’s threat degree. In a sparse data set many non-zero values are randomly spread in the entire data space. Hence, the challenge is to cluster the correlated patient’s record to predict the risk degree of the disease earlier than they occur in patients and to keep privacy. The first phase converts the sparse dataset right into a band matrix through the Genetic algorithm along with Cuckoo Search (GCS.This groups the correlated patient’s record together and arranges them close to the diagonal. The next segment dissociates the patient’s disease, which is a sensitive value (SA with the parameters that determine the disease normally Quasi Identifier (QI.Finally, density based clustering technique is used over the underlying data to  create anonymized groups to maintain privacy and to predict the risk level of disease. Empirical assessments on actual health care data corresponding to V.A.Medical Centre heart disease dataset reveal the efficiency of this model pertaining to information loss, utility and privacy.

Manifold regularization for sparse unmixing of hyperspectral images.

Science.gov (United States)

Liu, Junmin; Zhang, Chunxia; Zhang, Jiangshe; Li, Huirong; Gao, Yuelin

2016-01-01

Recently, sparse unmixing has been successfully applied to spectral mixture analysis of remotely sensed hyperspectral images. Based on the assumption that the observed image signatures can be expressed in the form of linear combinations of a number of pure spectral signatures known in advance, unmixing of each mixed pixel in the scene is to find an optimal subset of signatures in a very large spectral library, which is cast into the framework of sparse regression. However, traditional sparse regression models, such as collaborative sparse regression , ignore the intrinsic geometric structure in the hyperspectral data. In this paper, we propose a novel model, called manifold regularized collaborative sparse regression , by introducing a manifold regularization to the collaborative sparse regression model. The manifold regularization utilizes a graph Laplacian to incorporate the locally geometrical structure of the hyperspectral data. An algorithm based on alternating direction method of multipliers has been developed for the manifold regularized collaborative sparse regression model. Experimental results on both the simulated and real hyperspectral data sets have demonstrated the effectiveness of our proposed model.

Robust Single Image Super-Resolution via Deep Networks With Sparse Prior.

Science.gov (United States)

Liu, Ding; Wang, Zhaowen; Wen, Bihan; Yang, Jianchao; Han, Wei; Huang, Thomas S

2016-07-01

Single image super-resolution (SR) is an ill-posed problem, which tries to recover a high-resolution image from its low-resolution observation. To regularize the solution of the problem, previous methods have focused on designing good priors for natural images, such as sparse representation, or directly learning the priors from a large data set with models, such as deep neural networks. In this paper, we argue that domain expertise from the conventional sparse coding model can be combined with the key ingredients of deep learning to achieve further improved results. We demonstrate that a sparse coding model particularly designed for SR can be incarnated as a neural network with the merit of end-to-end optimization over training data. The network has a cascaded structure, which boosts the SR performance for both fixed and incremental scaling factors. The proposed training and testing schemes can be extended for robust handling of images with additional degradation, such as noise and blurring. A subjective assessment is conducted and analyzed in order to thoroughly evaluate various SR techniques. Our proposed model is tested on a wide range of images, and it significantly outperforms the existing state-of-the-art methods for various scaling factors both quantitatively and perceptually.

Regression with Sparse Approximations of Data

DEFF Research Database (Denmark)

Noorzad, Pardis; Sturm, Bob L.

2012-01-01

We propose sparse approximation weighted regression (SPARROW), a method for local estimation of the regression function that uses sparse approximation with a dictionary of measurements. SPARROW estimates the regression function at a point with a linear combination of a few regressands selected...... by a sparse approximation of the point in terms of the regressors. We show SPARROW can be considered a variant of \\(k\\)-nearest neighbors regression (\\(k\\)-NNR), and more generally, local polynomial kernel regression. Unlike \\(k\\)-NNR, however, SPARROW can adapt the number of regressors to use based...

Sparse adaptive filters for echo cancellation

CERN Document Server

Paleologu, Constantin

2011-01-01

Adaptive filters with a large number of coefficients are usually involved in both network and acoustic echo cancellation. Consequently, it is important to improve the convergence rate and tracking of the conventional algorithms used for these applications. This can be achieved by exploiting the sparseness character of the echo paths. Identification of sparse impulse responses was addressed mainly in the last decade with the development of the so-called ``proportionate''-type algorithms. The goal of this book is to present the most important sparse adaptive filters developed for echo cancellati

Sparse and Robust Factor Modelling

NARCIS (Netherlands)

C. Croux (Christophe); P. Exterkate (Peter)

2011-01-01

textabstractFactor construction methods are widely used to summarize a large panel of variables by means of a relatively small number of representative factors. We propose a novel factor construction procedure that enjoys the properties of robustness to outliers and of sparsity; that is, having

Nonnegative Matrix Factor 2-D Deconvolution for Blind Single Channel Source Separation

DEFF Research Database (Denmark)

Schmidt, Mikkel N.; Mørup, Morten

2006-01-01

We present a novel method for blind separation of instruments in polyphonic music based on a non-negative matrix factor 2-D deconvolution algorithm. Using a model which is convolutive in both time and frequency we factorize a spectrogram representation of music into components corresponding...

Visual recognition and inference using dynamic overcomplete sparse learning.

Science.gov (United States)

Murray, Joseph F; Kreutz-Delgado, Kenneth

2007-09-01

We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and expectation-driven segmentation. Using properties of biological vision for guidance, we posit a stochastic generative world model and from it develop a simplified world model (SWM) based on a tractable variational approximation that is designed to enforce sparse coding. Recent developments in computational methods for learning overcomplete representations (Lewicki & Sejnowski, 2000; Teh, Welling, Osindero, & Hinton, 2003) suggest that overcompleteness can be useful for visual tasks, and we use an overcomplete dictionary learning algorithm (Kreutz-Delgado, et al., 2003) as a preprocessing stage to produce accurate, sparse codings of images. Inference is performed by constructing a dynamic multilayer network with feedforward, feedback, and lateral connections, which is trained to approximate the SWM. Learning is done with a variant of the back-propagation-through-time algorithm, which encourages convergence to desired states within a fixed number of iterations. Vision tasks require large networks, and to make learning efficient, we take advantage of the sparsity of each layer to update only a small subset of elements in a large weight matrix at each iteration. Experiments on a set of rotated objects demonstrate various types of visual inference and show that increasing the degree of overcompleteness improves recognition performance in difficult scenes with occluded objects in clutter.

Sparse representation based image interpolation with nonlocal autoregressive modeling.

Science.gov (United States)

Dong, Weisheng; Zhang, Lei; Lukac, Rastislav; Shi, Guangming

2013-04-01

Sparse representation is proven to be a promising approach to image super-resolution, where the low-resolution (LR) image is usually modeled as the down-sampled version of its high-resolution (HR) counterpart after blurring. When the blurring kernel is the Dirac delta function, i.e., the LR image is directly down-sampled from its HR counterpart without blurring, the super-resolution problem becomes an image interpolation problem. In such cases, however, the conventional sparse representation models (SRM) become less effective, because the data fidelity term fails to constrain the image local structures. In natural images, fortunately, many nonlocal similar patches to a given patch could provide nonlocal constraint to the local structure. In this paper, we incorporate the image nonlocal self-similarity into SRM for image interpolation. More specifically, a nonlocal autoregressive model (NARM) is proposed and taken as the data fidelity term in SRM. We show that the NARM-induced sampling matrix is less coherent with the representation dictionary, and consequently makes SRM more effective for image interpolation. Our extensive experimental results demonstrate that the proposed NARM-based image interpolation method can effectively reconstruct the edge structures and suppress the jaggy/ringing artifacts, achieving the best image interpolation results so far in terms of PSNR as well as perceptual quality metrics such as SSIM and FSIM.

Large Covariance Estimation by Thresholding Principal Orthogonal Complements.

Science.gov (United States)

Fan, Jianqing; Liao, Yuan; Mincheva, Martina

2013-09-01

This paper deals with the estimation of a high-dimensional covariance with a conditional sparsity structure and fast-diverging eigenvalues. By assuming sparse error covariance matrix in an approximate factor model, we allow for the presence of some cross-sectional correlation even after taking out common but unobservable factors. We introduce the Principal Orthogonal complEment Thresholding (POET) method to explore such an approximate factor structure with sparsity. The POET estimator includes the sample covariance matrix, the factor-based covariance matrix (Fan, Fan, and Lv, 2008), the thresholding estimator (Bickel and Levina, 2008) and the adaptive thresholding estimator (Cai and Liu, 2011) as specific examples. We provide mathematical insights when the factor analysis is approximately the same as the principal component analysis for high-dimensional data. The rates of convergence of the sparse residual covariance matrix and the conditional sparse covariance matrix are studied under various norms. It is shown that the impact of estimating the unknown factors vanishes as the dimensionality increases. The uniform rates of convergence for the unobserved factors and their factor loadings are derived. The asymptotic results are also verified by extensive simulation studies. Finally, a real data application on portfolio allocation is presented.

Incomplete factorization technique for positive definite linear systems

International Nuclear Information System (INIS)

Manteuffel, T.A.

1980-01-01

This paper describes a technique for solving the large sparse symmetric linear systems that arise from the application of finite element methods. The technique combines an incomplete factorization method called the shifted incomplete Cholesky factorization with the method of generalized conjugate gradients. The shifted incomplete Cholesky factorization produces a splitting of the matrix A that is dependent upon a parameter α. It is shown that if A is positive definite, then there is some α for which this splitting is possible and that this splitting is at least as good as the Jacobi splitting. The method is shown to be more efficient on a set of test problems than either direct methods or explicit iteration schemes

Sparse optimization for inverse problems in atmospheric modelling

Czech Academy of Sciences Publication Activity Database

Adam, Lukáš; Branda, Martin

2016-01-01

Roč. 79, č. 3 (2016), s. 256-266 ISSN 1364-8152 R&D Projects: GA MŠk(CZ) 7F14287 Institutional support: RVO:67985556 Keywords : Inverse modelling * Sparse optimization * Integer optimization * Least squares * European tracer experiment * Free Matlab codes Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 4.404, year: 2016 http://library.utia.cas.cz/separaty/2016/MTR/adam-0457037.pdf

Human aqueous humor levels of transforming growth factor-β2: Association with matrix metalloproteinases/tissue inhibitors of matrix metalloproteinases

OpenAIRE

Jia, Yan; Yue, Yu; Hu, Dan-Ning; Chen, Ji-Li; Zhou, Ji-Bo

2017-01-01

The present study aims to investigate the association of transforming growth factor-β2 (TGF-β2) and matrix metalloproteinases (MMPs), MMP-2 and MMP-3, and tissue inhibitors of matrix metalloproteinases (TIMPs), TIMP-1, TIMP-2 and TIMP-3 in the aqueous humor of patients with high myopia or cataracts. The levels of TGF-β2 and MMPs/TIMPs were measured with the Luminex xMAP Technology using commercially available Milliplex xMAP kits. The association between TGF-β2 and MMPs/TIMPs levels was analyz...

Nonuniform Sparse Data Clustering Cascade Algorithm Based on Dynamic Cumulative Entropy

Directory of Open Access Journals (Sweden)

Ning Li

2016-01-01

Full Text Available A small amount of prior knowledge and randomly chosen initial cluster centers have a direct impact on the accuracy of the performance of iterative clustering algorithm. In this paper we propose a new algorithm to compute initial cluster centers for k-means clustering and the best number of the clusters with little prior knowledge and optimize clustering result. It constructs the Euclidean distance control factor based on aggregation density sparse degree to select the initial cluster center of nonuniform sparse data and obtains initial data clusters by multidimensional diffusion density distribution. Multiobjective clustering approach based on dynamic cumulative entropy is adopted to optimize the initial data clusters and the best number of the clusters. The experimental results show that the newly proposed algorithm has good performance to obtain the initial cluster centers for the k-means algorithm and it effectively improves the clustering accuracy of nonuniform sparse data by about 5%.

On the role of sparseness in the evolution of modularity in gene regulatory networks.

Science.gov (United States)

Espinosa-Soto, Carlos

2018-05-01

Modularity is a widespread property in biological systems. It implies that interactions occur mainly within groups of system elements. A modular arrangement facilitates adjustment of one module without perturbing the rest of the system. Therefore, modularity of developmental mechanisms is a major factor for evolvability, the potential to produce beneficial variation from random genetic change. Understanding how modularity evolves in gene regulatory networks, that create the distinct gene activity patterns that characterize different parts of an organism, is key to developmental and evolutionary biology. One hypothesis for the evolution of modules suggests that interactions between some sets of genes become maladaptive when selection favours additional gene activity patterns. The removal of such interactions by selection would result in the formation of modules. A second hypothesis suggests that modularity evolves in response to sparseness, the scarcity of interactions within a system. Here I simulate the evolution of gene regulatory networks and analyse diverse experimentally sustained networks to study the relationship between sparseness and modularity. My results suggest that sparseness alone is neither sufficient nor necessary to explain modularity in gene regulatory networks. However, sparseness amplifies the effects of forms of selection that, like selection for additional gene activity patterns, already produce an increase in modularity. That evolution of new gene activity patterns is frequent across evolution also supports that it is a major factor in the evolution of modularity. That sparseness is widespread across gene regulatory networks indicates that it may have facilitated the evolution of modules in a wide variety of cases.

Robust Face Recognition Via Gabor Feature and Sparse Representation

Directory of Open Access Journals (Sweden)

Hao Yu-Juan

2016-01-01

Full Text Available Sparse representation based on compressed sensing theory has been widely used in the field of face recognition, and has achieved good recognition results. but the face feature extraction based on sparse representation is too simple, and the sparse coefficient is not sparse. In this paper, we improve the classification algorithm based on the fusion of sparse representation and Gabor feature, and then improved algorithm for Gabor feature which overcomes the problem of large dimension of the vector dimension, reduces the computation and storage cost, and enhances the robustness of the algorithm to the changes of the environment.The classification efficiency of sparse representation is determined by the collaborative representation,we simplify the sparse constraint based on L1 norm to the least square constraint, which makes the sparse coefficients both positive and reduce the complexity of the algorithm. Experimental results show that the proposed method is robust to illumination, facial expression and pose variations of face recognition, and the recognition rate of the algorithm is improved.

Sparse Learning with Stochastic Composite Optimization.

Science.gov (United States)

Zhang, Weizhong; Zhang, Lijun; Jin, Zhongming; Jin, Rong; Cai, Deng; Li, Xuelong; Liang, Ronghua; He, Xiaofei

2017-06-01

In this paper, we study Stochastic Composite Optimization (SCO) for sparse learning that aims to learn a sparse solution from a composite function. Most of the recent SCO algorithms have already reached the optimal expected convergence rate O(1/λT), but they often fail to deliver sparse solutions at the end either due to the limited sparsity regularization during stochastic optimization (SO) or due to the limitation in online-to-batch conversion. Even when the objective function is strongly convex, their high probability bounds can only attain O(√{log(1/δ)/T}) with δ is the failure probability, which is much worse than the expected convergence rate. To address these limitations, we propose a simple yet effective two-phase Stochastic Composite Optimization scheme by adding a novel powerful sparse online-to-batch conversion to the general Stochastic Optimization algorithms. We further develop three concrete algorithms, OptimalSL, LastSL and AverageSL, directly under our scheme to prove the effectiveness of the proposed scheme. Both the theoretical analysis and the experiment results show that our methods can really outperform the existing methods at the ability of sparse learning and at the meantime we can improve the high probability bound to approximately O(log(log(T)/δ)/λT).

Shearlets and Optimally Sparse Approximations

DEFF Research Database (Denmark)

Kutyniok, Gitta; Lemvig, Jakob; Lim, Wang-Q

2012-01-01

Multivariate functions are typically governed by anisotropic features such as edges in images or shock fronts in solutions of transport-dominated equations. One major goal both for the purpose of compression as well as for an efficient analysis is the provision of optimally sparse approximations...... optimally sparse approximations of this model class in 2D as well as 3D. Even more, in contrast to all other directional representation systems, a theory for compactly supported shearlet frames was derived which moreover also satisfy this optimality benchmark. This chapter shall serve as an introduction...... to and a survey about sparse approximations of cartoon-like images by band-limited and also compactly supported shearlet frames as well as a reference for the state-of-the-art of this research field....

Mixed Far-Field and Near-Field Source Localization Algorithm via Sparse Subarrays

Directory of Open Access Journals (Sweden)

Jiaqi Song

2018-01-01

Full Text Available Based on a dual-size shift invariance sparse linear array, this paper presents a novel algorithm for the localization of mixed far-field and near-field sources. First, by constructing a cumulant matrix with only direction-of-arrival (DOA information, the proposed algorithm decouples the DOA estimation from the range estimation. The cumulant-domain quarter-wavelength invariance yields unambiguous estimates of DOAs, which are then used as coarse references to disambiguate the phase ambiguities in fine estimates induced from the larger spatial invariance. Then, based on the estimated DOAs, another cumulant matrix is derived and decoupled to generate unambiguous and cyclically ambiguous estimates of range parameter. According to the coarse range estimation, the types of sources can be identified and the unambiguous fine range estimates of NF sources are obtained after disambiguation. Compared with some existing algorithms, the proposed algorithm enjoys extended array aperture and higher estimation accuracy. Simulation results are given to validate the performance of the proposed algorithm.

Multilevel sparse functional principal component analysis.

Science.gov (United States)

Di, Chongzhi; Crainiceanu, Ciprian M; Jank, Wolfgang S

2014-01-29

We consider analysis of sparsely sampled multilevel functional data, where the basic observational unit is a function and data have a natural hierarchy of basic units. An example is when functions are recorded at multiple visits for each subject. Multilevel functional principal component analysis (MFPCA; Di et al. 2009) was proposed for such data when functions are densely recorded. Here we consider the case when functions are sparsely sampled and may contain only a few observations per function. We exploit the multilevel structure of covariance operators and achieve data reduction by principal component decompositions at both between and within subject levels. We address inherent methodological differences in the sparse sampling context to: 1) estimate the covariance operators; 2) estimate the functional principal component scores; 3) predict the underlying curves. Through simulations the proposed method is able to discover dominating modes of variations and reconstruct underlying curves well even in sparse settings. Our approach is illustrated by two applications, the Sleep Heart Health Study and eBay auctions.

A sparse version of IGA solvers

KAUST Repository

Beck, Joakim; Sangalli, Giancarlo; Tamellini, Lorenzo

2017-01-01

Isogeometric Analysis (IGA) typically adopts tensor-product splines and NURBS as a basis for the approximation of the solution of PDEs. In this work, we investigate to which extent IGA solvers can benefit from the so-called sparse-grids construction in its combination technique form, which was first introduced in the early 90s in the context of the approximation of high-dimensional PDEs. The tests that we report show that, in accordance to the literature, a sparse grids construction can indeed be useful if the solution of the PDE at hand is sufficiently smooth. Sparse grids can also be useful in the case of non-smooth solutions when some a-priori knowledge on the location of the singularities of the solution can be exploited to devise suitable non-equispaced meshes. Finally, we remark that sparse grids can be seen as a simple way to parallelize pre-existing serial IGA solvers in a straightforward fashion, which can be beneficial in many practical situations.

A sparse version of IGA solvers

KAUST Repository

Beck, Joakim

2017-07-30

Isogeometric Analysis (IGA) typically adopts tensor-product splines and NURBS as a basis for the approximation of the solution of PDEs. In this work, we investigate to which extent IGA solvers can benefit from the so-called sparse-grids construction in its combination technique form, which was first introduced in the early 90s in the context of the approximation of high-dimensional PDEs. The tests that we report show that, in accordance to the literature, a sparse grids construction can indeed be useful if the solution of the PDE at hand is sufficiently smooth. Sparse grids can also be useful in the case of non-smooth solutions when some a-priori knowledge on the location of the singularities of the solution can be exploited to devise suitable non-equispaced meshes. Finally, we remark that sparse grids can be seen as a simple way to parallelize pre-existing serial IGA solvers in a straightforward fashion, which can be beneficial in many practical situations.

Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation

Directory of Open Access Journals (Sweden)

Qu Li

2014-01-01

Full Text Available Online friend recommendation is a fast developing topic in web mining. In this paper, we used SVD matrix factorization to model user and item feature vector and used stochastic gradient descent to amend parameter and improve accuracy. To tackle cold start problem and data sparsity, we used KNN model to influence user feature vector. At the same time, we used graph theory to partition communities with fairly low time and space complexity. What is more, matrix factorization can combine online and offline recommendation. Experiments showed that the hybrid recommendation algorithm is able to recommend online friends with good accuracy.

Language Recognition via Sparse Coding

Science.gov (United States)

2016-09-08

explanation is that sparse coding can achieve a near-optimal approximation of much complicated nonlinear relationship through local and piecewise linear...training examples, where x(i) ∈ RN is the ith example in the batch. Optionally, X can be normalized and whitened before sparse coding for better result...normalized input vectors are then ZCA- whitened [20]. Em- pirically, we choose ZCA- whitening over PCA- whitening , and there is no dimensionality reduction

Two-stage sparse coding of region covariance via Log-Euclidean kernels to detect saliency.

Science.gov (United States)

Zhang, Ying-Ying; Yang, Cai; Zhang, Ping

2017-05-01

In this paper, we present a novel bottom-up saliency detection algorithm from the perspective of covariance matrices on a Riemannian manifold. Each superpixel is described by a region covariance matrix on Riemannian Manifolds. We carry out a two-stage sparse coding scheme via Log-Euclidean kernels to extract salient objects efficiently. In the first stage, given background dictionary on image borders, sparse coding of each region covariance via Log-Euclidean kernels is performed. The reconstruction error on the background dictionary is regarded as the initial saliency of each superpixel. In the second stage, an improvement of the initial result is achieved by calculating reconstruction errors of the superpixels on foreground dictionary, which is extracted from the first stage saliency map. The sparse coding in the second stage is similar to the first stage, but is able to effectively highlight the salient objects uniformly from the background. Finally, three post-processing methods-highlight-inhibition function, context-based saliency weighting, and the graph cut-are adopted to further refine the saliency map. Experiments on four public benchmark datasets show that the proposed algorithm outperforms the state-of-the-art methods in terms of precision, recall and mean absolute error, and demonstrate the robustness and efficiency of the proposed method. Copyright © 2017 Elsevier Ltd. All rights reserved.

Sparse seismic imaging using variable projection

NARCIS (Netherlands)

Aravkin, Aleksandr Y.; Tu, Ning; van Leeuwen, Tristan

2013-01-01

We consider an important class of signal processing problems where the signal of interest is known to be sparse, and can be recovered from data given auxiliary information about how the data was generated. For example, a sparse Green's function may be recovered from seismic experimental data using

Tunable Sparse Network Coding for Multicast Networks

DEFF Research Database (Denmark)

Feizi, Soheil; Roetter, Daniel Enrique Lucani; Sørensen, Chres Wiant

2014-01-01

This paper shows the potential and key enabling mechanisms for tunable sparse network coding, a scheme in which the density of network coded packets varies during a transmission session. At the beginning of a transmission session, sparsely coded packets are transmitted, which benefits decoding...... complexity. At the end of a transmission, when receivers have accumulated degrees of freedom, coding density is increased. We propose a family of tunable sparse network codes (TSNCs) for multicast erasure networks with a controllable trade-off between completion time performance to decoding complexity...... a mechanism to perform efficient Gaussian elimination over sparse matrices going beyond belief propagation but maintaining low decoding complexity. Supporting simulation results are provided showing the trade-off between decoding complexity and completion time....

Bayesian inference of the number of factors in gene-expression analysis: application to human virus challenge studies

Directory of Open Access Journals (Sweden)

Hero Alfred

2010-11-01

Full Text Available Abstract Background Nonparametric Bayesian techniques have been developed recently to extend the sophistication of factor models, allowing one to infer the number of appropriate factors from the observed data. We consider such techniques for sparse factor analysis, with application to gene-expression data from three virus challenge studies. Particular attention is placed on employing the Beta Process (BP, the Indian Buffet Process (IBP, and related sparseness-promoting techniques to infer a proper number of factors. The posterior density function on the model parameters is computed using Gibbs sampling and variational Bayesian (VB analysis. Results Time-evolving gene-expression data are considered for respiratory syncytial virus (RSV, Rhino virus, and influenza, using blood samples from healthy human subjects. These data were acquired in three challenge studies, each executed after receiving institutional review board (IRB approval from Duke University. Comparisons are made between several alternative means of per-forming nonparametric factor analysis on these data, with comparisons as well to sparse-PCA and Penalized Matrix Decomposition (PMD, closely related non-Bayesian approaches. Conclusions Applying the Beta Process to the factor scores, or to the singular values of a pseudo-SVD construction, the proposed algorithms infer the number of factors in gene-expression data. For real data the "true" number of factors is unknown; in our simulations we consider a range of noise variances, and the proposed Bayesian models inferred the number of factors accurately relative to other methods in the literature, such as sparse-PCA and PMD. We have also identified a "pan-viral" factor of importance for each of the three viruses considered in this study. We have identified a set of genes associated with this pan-viral factor, of interest for early detection of such viruses based upon the host response, as quantified via gene-expression data.

Bayesian inference of the number of factors in gene-expression analysis: application to human virus challenge studies.

Science.gov (United States)

Chen, Bo; Chen, Minhua; Paisley, John; Zaas, Aimee; Woods, Christopher; Ginsburg, Geoffrey S; Hero, Alfred; Lucas, Joseph; Dunson, David; Carin, Lawrence

2010-11-09

Nonparametric Bayesian techniques have been developed recently to extend the sophistication of factor models, allowing one to infer the number of appropriate factors from the observed data. We consider such techniques for sparse factor analysis, with application to gene-expression data from three virus challenge studies. Particular attention is placed on employing the Beta Process (BP), the Indian Buffet Process (IBP), and related sparseness-promoting techniques to infer a proper number of factors. The posterior density function on the model parameters is computed using Gibbs sampling and variational Bayesian (VB) analysis. Time-evolving gene-expression data are considered for respiratory syncytial virus (RSV), Rhino virus, and influenza, using blood samples from healthy human subjects. These data were acquired in three challenge studies, each executed after receiving institutional review board (IRB) approval from Duke University. Comparisons are made between several alternative means of per-forming nonparametric factor analysis on these data, with comparisons as well to sparse-PCA and Penalized Matrix Decomposition (PMD), closely related non-Bayesian approaches. Applying the Beta Process to the factor scores, or to the singular values of a pseudo-SVD construction, the proposed algorithms infer the number of factors in gene-expression data. For real data the "true" number of factors is unknown; in our simulations we consider a range of noise variances, and the proposed Bayesian models inferred the number of factors accurately relative to other methods in the literature, such as sparse-PCA and PMD. We have also identified a "pan-viral" factor of importance for each of the three viruses considered in this study. We have identified a set of genes associated with this pan-viral factor, of interest for early detection of such viruses based upon the host response, as quantified via gene-expression data.

Novel Fourier-based iterative reconstruction for sparse fan projection using alternating direction total variation minimization

International Nuclear Information System (INIS)

Jin Zhao; Zhang Han-Ming; Yan Bin; Li Lei; Wang Lin-Yuan; Cai Ai-Long

2016-01-01

Sparse-view x-ray computed tomography (CT) imaging is an interesting topic in CT field and can efficiently decrease radiation dose. Compared with spatial reconstruction, a Fourier-based algorithm has advantages in reconstruction speed and memory usage. A novel Fourier-based iterative reconstruction technique that utilizes non-uniform fast Fourier transform (NUFFT) is presented in this work along with advanced total variation (TV) regularization for a fan sparse-view CT. The proposition of a selective matrix contributes to improve reconstruction quality. The new method employs the NUFFT and its adjoin to iterate back and forth between the Fourier and image space. The performance of the proposed algorithm is demonstrated through a series of digital simulations and experimental phantom studies. Results of the proposed algorithm are compared with those of existing TV-regularized techniques based on compressed sensing method, as well as basic algebraic reconstruction technique. Compared with the existing TV-regularized techniques, the proposed Fourier-based technique significantly improves convergence rate and reduces memory allocation, respectively. (paper)

Structural Sparse Tracking

KAUST Repository

Zhang, Tianzhu; Yang, Ming-Hsuan; Ahuja, Narendra; Ghanem, Bernard; Yan, Shuicheng; Xu, Changsheng; Liu, Si

2015-01-01

candidate. We show that our SST algorithm accommodates most existing sparse trackers with the respective merits. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SST algorithm performs

Regulation of proliferation of embryonic heart mesenchyme: Role of transforming growth factor-beta 1 and the interstitial matrix

International Nuclear Information System (INIS)

Choy, M.; Armstrong, M.T.; Armstrong, P.B.

1990-01-01

Proliferation of atrioventricular cushion mesenchyme of the embryonic avian heart maintained in three-dimensional aggregate culture is stimulated by interaction with the interstitial matrix. Chicken serum or transforming growth factor-beta 1, which stimulates proliferation, induces matrix deposition in regions of the aggregate showing high labeling indices with tritiated thymidine. Dispersed heart mesenchyme interstitial matrix introduced into serum-free culture is incorporated into the aggregate and stimulates cellular proliferation similar to serum or transforming growth factor-beta 1. Proliferation is reversibly inhibited by the peptide Gly-Arg-Gly-Asp-Ser-Pro. It is suggested that transforming growth factor-beta 1 stimulates the production of interstitial matrix and that a sufficient stimulus for proliferation in this system is the presence of the matrix, which acts as the adhesive support for cellular anchorage

Sparse Representations of Hyperspectral Images

KAUST Repository

Swanson, Robin J.

2015-11-23

Hyperspectral image data has long been an important tool for many areas of sci- ence. The addition of spectral data yields significant improvements in areas such as object and image classification, chemical and mineral composition detection, and astronomy. Traditional capture methods for hyperspectral data often require each wavelength to be captured individually, or by sacrificing spatial resolution. Recently there have been significant improvements in snapshot hyperspectral captures using, in particular, compressed sensing methods. As we move to a compressed sensing image formation model the need for strong image priors to shape our reconstruction, as well as sparse basis become more important. Here we compare several several methods for representing hyperspectral images including learned three dimensional dictionaries, sparse convolutional coding, and decomposable nonlocal tensor dictionaries. Addi- tionally, we further explore their parameter space to identify which parameters provide the most faithful and sparse representations.

Sparse Representations of Hyperspectral Images

KAUST Repository

Swanson, Robin J.

2015-01-01

Hyperspectral image data has long been an important tool for many areas of sci- ence. The addition of spectral data yields significant improvements in areas such as object and image classification, chemical and mineral composition detection, and astronomy. Traditional capture methods for hyperspectral data often require each wavelength to be captured individually, or by sacrificing spatial resolution. Recently there have been significant improvements in snapshot hyperspectral captures using, in particular, compressed sensing methods. As we move to a compressed sensing image formation model the need for strong image priors to shape our reconstruction, as well as sparse basis become more important. Here we compare several several methods for representing hyperspectral images including learned three dimensional dictionaries, sparse convolutional coding, and decomposable nonlocal tensor dictionaries. Addi- tionally, we further explore their parameter space to identify which parameters provide the most faithful and sparse representations.

Supervised Convolutional Sparse Coding

KAUST Repository

Affara, Lama Ahmed

2018-04-08

Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional sparse coding, which aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminative. Experimental results show that using supervised convolutional learning results in two key advantages. First, we learn more semantically relevant filters in the dictionary and second, we achieve improved image reconstruction on unseen data.

Segmentation of High Angular Resolution Diffusion MRI using Sparse Riemannian Manifold Clustering

Science.gov (United States)

Wright, Margaret J.; Thompson, Paul M.; Vidal, René

2015-01-01

We address the problem of segmenting high angular resolution diffusion imaging (HARDI) data into multiple regions (or fiber tracts) with distinct diffusion properties. We use the orientation distribution function (ODF) to represent HARDI data and cast the problem as a clustering problem in the space of ODFs. Our approach integrates tools from sparse representation theory and Riemannian geometry into a graph theoretic segmentation framework. By exploiting the Riemannian properties of the space of ODFs, we learn a sparse representation for each ODF and infer the segmentation by applying spectral clustering to a similarity matrix built from these representations. In cases where regions with similar (resp. distinct) diffusion properties belong to different (resp. same) fiber tracts, we obtain the segmentation by incorporating spatial and user-specified pairwise relationships into the formulation. Experiments on synthetic data evaluate the sensitivity of our method to image noise and the presence of complex fiber configurations, and show its superior performance compared to alternative segmentation methods. Experiments on phantom and real data demonstrate the accuracy of the proposed method in segmenting simulated fibers, as well as white matter fiber tracts of clinical importance in the human brain. PMID:24108748

Structure-aware Local Sparse Coding for Visual Tracking

KAUST Repository

Qi, Yuankai

2018-01-24

Sparse coding has been applied to visual tracking and related vision problems with demonstrated success in recent years. Existing tracking methods based on local sparse coding sample patches from a target candidate and sparsely encode these using a dictionary consisting of patches sampled from target template images. The discriminative strength of existing methods based on local sparse coding is limited as spatial structure constraints among the template patches are not exploited. To address this problem, we propose a structure-aware local sparse coding algorithm which encodes a target candidate using templates with both global and local sparsity constraints. For robust tracking, we show local regions of a candidate region should be encoded only with the corresponding local regions of the target templates that are the most similar from the global view. Thus, a more precise and discriminative sparse representation is obtained to account for appearance changes. To alleviate the issues with tracking drifts, we design an effective template update scheme. Extensive experiments on challenging image sequences demonstrate the effectiveness of the proposed algorithm against numerous stateof- the-art methods.

Advanced incomplete factorization algorithms for Stiltijes matrices

Energy Technology Data Exchange (ETDEWEB)

Il`in, V.P. [Siberian Division RAS, Novosibirsk (Russian Federation)

1996-12-31

The modern numerical methods for solving the linear algebraic systems Au = f with high order sparse matrices A, which arise in grid approximations of multidimensional boundary value problems, are based mainly on accelerated iterative processes with easily invertible preconditioning matrices presented in the form of approximate (incomplete) factorization of the original matrix A. We consider some recent algorithmic approaches, theoretical foundations, experimental data and open questions for incomplete factorization of Stiltijes matrices which are {open_quotes}the best{close_quotes} ones in the sense that they have the most advanced results. Special attention is given to solving the elliptic differential equations with strongly variable coefficients, singular perturbated diffusion-convection and parabolic equations.

Single-Trial Decoding of Bistable Perception Based on Sparse Nonnegative Tensor Decomposition

Science.gov (United States)

Wang, Zhisong; Maier, Alexander; Logothetis, Nikos K.; Liang, Hualou

2008-01-01

The study of the neuronal correlates of the spontaneous alternation in perception elicited by bistable visual stimuli is promising for understanding the mechanism of neural information processing and the neural basis of visual perception and perceptual decision-making. In this paper, we develop a sparse nonnegative tensor factorization-(NTF)-based method to extract features from the local field potential (LFP), collected from the middle temporal (MT) visual cortex in a macaque monkey, for decoding its bistable structure-from-motion (SFM) perception. We apply the feature extraction approach to the multichannel time-frequency representation of the intracortical LFP data. The advantages of the sparse NTF-based feature extraction approach lies in its capability to yield components common across the space, time, and frequency domains yet discriminative across different conditions without prior knowledge of the discriminating frequency bands and temporal windows for a specific subject. We employ the support vector machines (SVMs) classifier based on the features of the NTF components for single-trial decoding the reported perception. Our results suggest that although other bands also have certain discriminability, the gamma band feature carries the most discriminative information for bistable perception, and that imposing the sparseness constraints on the nonnegative tensor factorization improves extraction of this feature. PMID:18528515

Cross-correlation matrix analysis of Chinese and American bank stocks in subprime crisis

Science.gov (United States)

Zhu, Shi-Zhao; Li, Xin-Li; Nie, Sen; Zhang, Wen-Qing; Yu, Gao-Feng; Han, Xiao-Pu; Wang, Bing-Hong

2015-05-01

In order to study the universality of the interactions among different markets, we analyze the cross-correlation matrix of the price of the Chinese and American bank stocks. We then find that the stock prices of the emerging market are more correlated than that of the developed market. Considering that the values of the components for the eigenvector may be positive or negative, we analyze the differences between two markets in combination with the endogenous and exogenous events which influence the financial markets. We find that the sparse pattern of components of eigenvectors out of the threshold value has no change in American bank stocks before and after the subprime crisis. However, it changes from sparse to dense for Chinese bank stocks. By using the threshold value to exclude the external factors, we simulate the interactions in financial markets. Project supported by the National Natural Science Foundation of China (Grant Nos. 11275186, 91024026, and FOM2014OF001) and the University of Shanghai for Science and Technology (USST) of Humanities and Social Sciences, China (Grant Nos. USST13XSZ05 and 11YJA790231).

Decentralized modal identification using sparse blind source separation

International Nuclear Information System (INIS)

Sadhu, A; Hazra, B; Narasimhan, S; Pandey, M D

2011-01-01

Popular ambient vibration-based system identification methods process information collected from a dense array of sensors centrally to yield the modal properties. In such methods, the need for a centralized processing unit capable of satisfying large memory and processing demands is unavoidable. With the advent of wireless smart sensor networks, it is now possible to process information locally at the sensor level, instead. The information at the individual sensor level can then be concatenated to obtain the global structure characteristics. A novel decentralized algorithm based on wavelet transforms to infer global structure mode information using measurements obtained using a small group of sensors at a time is proposed in this paper. The focus of the paper is on algorithmic development, while the actual hardware and software implementation is not pursued here. The problem of identification is cast within the framework of under-determined blind source separation invoking transformations of measurements to the time–frequency domain resulting in a sparse representation. The partial mode shape coefficients so identified are then combined to yield complete modal information. The transformations are undertaken using stationary wavelet packet transform (SWPT), yielding a sparse representation in the wavelet domain. Principal component analysis (PCA) is then performed on the resulting wavelet coefficients, yielding the partial mixing matrix coefficients from a few measurement channels at a time. This process is repeated using measurements obtained from multiple sensor groups, and the results so obtained from each group are concatenated to obtain the global modal characteristics of the structure

Decentralized modal identification using sparse blind source separation

Science.gov (United States)

Sadhu, A.; Hazra, B.; Narasimhan, S.; Pandey, M. D.

2011-12-01

Popular ambient vibration-based system identification methods process information collected from a dense array of sensors centrally to yield the modal properties. In such methods, the need for a centralized processing unit capable of satisfying large memory and processing demands is unavoidable. With the advent of wireless smart sensor networks, it is now possible to process information locally at the sensor level, instead. The information at the individual sensor level can then be concatenated to obtain the global structure characteristics. A novel decentralized algorithm based on wavelet transforms to infer global structure mode information using measurements obtained using a small group of sensors at a time is proposed in this paper. The focus of the paper is on algorithmic development, while the actual hardware and software implementation is not pursued here. The problem of identification is cast within the framework of under-determined blind source separation invoking transformations of measurements to the time-frequency domain resulting in a sparse representation. The partial mode shape coefficients so identified are then combined to yield complete modal information. The transformations are undertaken using stationary wavelet packet transform (SWPT), yielding a sparse representation in the wavelet domain. Principal component analysis (PCA) is then performed on the resulting wavelet coefficients, yielding the partial mixing matrix coefficients from a few measurement channels at a time. This process is repeated using measurements obtained from multiple sensor groups, and the results so obtained from each group are concatenated to obtain the global modal characteristics of the structure.

Sparse Frequency Waveform Design for Radar-Embedded Communication

Directory of Open Access Journals (Sweden)

Chaoyun Mai

2016-01-01

Full Text Available According to the Tag application with function of covert communication, a method for sparse frequency waveform design based on radar-embedded communication is proposed. Firstly, sparse frequency waveforms are designed based on power spectral density fitting and quasi-Newton method. Secondly, the eigenvalue decomposition of the sparse frequency waveform sequence is used to get the dominant space. Finally the communication waveforms are designed through the projection of orthogonal pseudorandom vectors in the vertical subspace. Compared with the linear frequency modulation waveform, the sparse frequency waveform can further improve the bandwidth occupation of communication signals, thus achieving higher communication rate. A certain correlation exists between the reciprocally orthogonal communication signals samples and the sparse frequency waveform, which guarantees the low SER (signal error rate and LPI (low probability of intercept. The simulation results verify the effectiveness of this method.

Interface discontinuity factors in the modal Eigenspace of the multigroup diffusion matrix

International Nuclear Information System (INIS)

Garcia-Herranz, N.; Herrero, J.J.; Cuervo, D.; Ahnert, C.

2011-01-01

Interface discontinuity factors based on the Generalized Equivalence Theory are commonly used in nodal homogenized diffusion calculations so that diffusion average values approximate heterogeneous higher order solutions. In this paper, an additional form of interface correction factors is presented in the frame of the Analytic Coarse Mesh Finite Difference Method (ACMFD), based on a correction of the modal fluxes instead of the physical fluxes. In the ACMFD formulation, implemented in COBAYA3 code, the coupled multigroup diffusion equations inside a homogenized region are reduced to a set of uncoupled modal equations through diagonalization of the multigroup diffusion matrix. Then, physical fluxes are transformed into modal fluxes in the Eigenspace of the diffusion matrix. It is possible to introduce interface flux discontinuity jumps as the difference of heterogeneous and homogeneous modal fluxes instead of introducing interface discontinuity factors as the ratio of heterogeneous and homogeneous physical fluxes. The formulation in the modal space has been implemented in COBAYA3 code and assessed by comparison with solutions using classical interface discontinuity factors in the physical space. (author)

Using Dynamic Multi-Task Non-Negative Matrix Factorization to Detect the Evolution of User Preferences in Collaborative Filtering.

Directory of Open Access Journals (Sweden)

Bin Ju

Full Text Available Predicting what items will be selected by a target user in the future is an important function for recommendation systems. Matrix factorization techniques have been shown to achieve good performance on temporal rating-type data, but little is known about temporal item selection data. In this paper, we developed a unified model that combines Multi-task Non-negative Matrix Factorization and Linear Dynamical Systems to capture the evolution of user preferences. Specifically, user and item features are projected into latent factor space by factoring co-occurrence matrices into a common basis item-factor matrix and multiple factor-user matrices. Moreover, we represented both within and between relationships of multiple factor-user matrices using a state transition matrix to capture the changes in user preferences over time. The experiments show that our proposed algorithm outperforms the other algorithms on two real datasets, which were extracted from Netflix movies and Last.fm music. Furthermore, our model provides a novel dynamic topic model for tracking the evolution of the behavior of a user over time.

Using Dynamic Multi-Task Non-Negative Matrix Factorization to Detect the Evolution of User Preferences in Collaborative Filtering.

Science.gov (United States)

Ju, Bin; Qian, Yuntao; Ye, Minchao; Ni, Rong; Zhu, Chenxi

2015-01-01

Predicting what items will be selected by a target user in the future is an important function for recommendation systems. Matrix factorization techniques have been shown to achieve good performance on temporal rating-type data, but little is known about temporal item selection data. In this paper, we developed a unified model that combines Multi-task Non-negative Matrix Factorization and Linear Dynamical Systems to capture the evolution of user preferences. Specifically, user and item features are projected into latent factor space by factoring co-occurrence matrices into a common basis item-factor matrix and multiple factor-user matrices. Moreover, we represented both within and between relationships of multiple factor-user matrices using a state transition matrix to capture the changes in user preferences over time. The experiments show that our proposed algorithm outperforms the other algorithms on two real datasets, which were extracted from Netflix movies and Last.fm music. Furthermore, our model provides a novel dynamic topic model for tracking the evolution of the behavior of a user over time.

Large Covariance Estimation by Thresholding Principal Orthogonal Complements

Science.gov (United States)

Fan, Jianqing; Liao, Yuan; Mincheva, Martina

2012-01-01

This paper deals with the estimation of a high-dimensional covariance with a conditional sparsity structure and fast-diverging eigenvalues. By assuming sparse error covariance matrix in an approximate factor model, we allow for the presence of some cross-sectional correlation even after taking out common but unobservable factors. We introduce the Principal Orthogonal complEment Thresholding (POET) method to explore such an approximate factor structure with sparsity. The POET estimator includes the sample covariance matrix, the factor-based covariance matrix (Fan, Fan, and Lv, 2008), the thresholding estimator (Bickel and Levina, 2008) and the adaptive thresholding estimator (Cai and Liu, 2011) as specific examples. We provide mathematical insights when the factor analysis is approximately the same as the principal component analysis for high-dimensional data. The rates of convergence of the sparse residual covariance matrix and the conditional sparse covariance matrix are studied under various norms. It is shown that the impact of estimating the unknown factors vanishes as the dimensionality increases. The uniform rates of convergence for the unobserved factors and their factor loadings are derived. The asymptotic results are also verified by extensive simulation studies. Finally, a real data application on portfolio allocation is presented. PMID:24348088

Effects of sparse sampling schemes on image quality in low-dose CT

International Nuclear Information System (INIS)

Abbas, Sajid; Lee, Taewon; Cho, Seungryong; Shin, Sukyoung; Lee, Rena

2013-01-01

Purpose: Various scanning methods and image reconstruction algorithms are actively investigated for low-dose computed tomography (CT) that can potentially reduce a health-risk related to radiation dose. Particularly, compressive-sensing (CS) based algorithms have been successfully developed for reconstructing images from sparsely sampled data. Although these algorithms have shown promises in low-dose CT, it has not been studied how sparse sampling schemes affect image quality in CS-based image reconstruction. In this work, the authors present several sparse-sampling schemes for low-dose CT, quantitatively analyze their data property, and compare effects of the sampling schemes on the image quality.Methods: Data properties of several sampling schemes are analyzed with respect to the CS-based image reconstruction using two measures: sampling density and data incoherence. The authors present five different sparse sampling schemes, and simulated those schemes to achieve a targeted dose reduction. Dose reduction factors of about 75% and 87.5%, compared to a conventional scan, were tested. A fully sampled circular cone-beam CT data set was used as a reference, and sparse sampling has been realized numerically based on the CBCT data.Results: It is found that both sampling density and data incoherence affect the image quality in the CS-based reconstruction. Among the sampling schemes the authors investigated, the sparse-view, many-view undersampling (MVUS)-fine, and MVUS-moving cases have shown promising results. These sampling schemes produced images with similar image quality compared to the reference image and their structure similarity index values were higher than 0.92 in the mouse head scan with 75% dose reduction.Conclusions: The authors found that in CS-based image reconstructions both sampling density and data incoherence affect the image quality, and suggest that a sampling scheme should be devised and optimized by use of these indicators. With this strategic

Structure and stability of genetic variance-covariance matrices: A Bayesian sparse factor analysis of transcriptional variation in the three-spined stickleback.

Science.gov (United States)

Siren, J; Ovaskainen, O; Merilä, J

2017-10-01

The genetic variance-covariance matrix (G) is a quantity of central importance in evolutionary biology due to its influence on the rate and direction of multivariate evolution. However, the predictive power of empirically estimated G-matrices is limited for two reasons. First, phenotypes are high-dimensional, whereas traditional statistical methods are tuned to estimate and analyse low-dimensional matrices. Second, the stability of G to environmental effects and over time remains poorly understood. Using Bayesian sparse factor analysis (BSFG) designed to estimate high-dimensional G-matrices, we analysed levels variation and covariation in 10,527 expressed genes in a large (n = 563) half-sib breeding design of three-spined sticklebacks subject to two temperature treatments. We found significant differences in the structure of G between the treatments: heritabilities and evolvabilities were higher in the warm than in the low-temperature treatment, suggesting more and faster opportunity to evolve in warm (stressful) conditions. Furthermore, comparison of G and its phenotypic equivalent P revealed the latter is a poor substitute of the former. Most strikingly, the results suggest that the expected impact of G on evolvability-as well as the similarity among G-matrices-may depend strongly on the number of traits included into analyses. In our results, the inclusion of only few traits in the analyses leads to underestimation in the differences between the G-matrices and their predicted impacts on evolution. While the results highlight the challenges involved in estimating G, they also illustrate that by enabling the estimation of large G-matrices, the BSFG method can improve predicted evolutionary responses to selection. © 2017 John Wiley & Sons Ltd.

Group sparse canonical correlation analysis for genomic data integration.

Science.gov (United States)

Lin, Dongdong; Zhang, Jigang; Li, Jingyao; Calhoun, Vince D; Deng, Hong-Wen; Wang, Yu-Ping

2013-08-12

The emergence of high-throughput genomic datasets from different sources and platforms (e.g., gene expression, single nucleotide polymorphisms (SNP), and copy number variation (CNV)) has greatly enhanced our understandings of the interplay of these genomic factors as well as their influences on the complex diseases. It is challenging to explore the relationship between these different types of genomic data sets. In this paper, we focus on a multivariate statistical method, canonical correlation analysis (CCA) method for this problem. Conventional CCA method does not work effectively if the number of data samples is significantly less than that of biomarkers, which is a typical case for genomic data (e.g., SNPs). Sparse CCA (sCCA) methods were introduced to overcome such difficulty, mostly using penalizations with l-1 norm (CCA-l1) or the combination of l-1and l-2 norm (CCA-elastic net). However, they overlook the structural or group effect within genomic data in the analysis, which often exist and are important (e.g., SNPs spanning a gene interact and work together as a group). We propose a new group sparse CCA method (CCA-sparse group) along with an effective numerical algorithm to study the mutual relationship between two different types of genomic data (i.e., SNP and gene expression). We then extend the model to a more general formulation that can include the existing sCCA models. We apply the model to feature/variable selection from two data sets and compare our group sparse CCA method with existing sCCA methods on both simulation and two real datasets (human gliomas data and NCI60 data). We use a graphical representation of the samples with a pair of canonical variates to demonstrate the discriminating characteristic of the selected features. Pathway analysis is further performed for biological interpretation of those features. The CCA-sparse group method incorporates group effects of features into the correlation analysis while performs individual feature

A reduced-scaling density matrix-based method for the computation of the vibrational Hessian matrix at the self-consistent field level

International Nuclear Information System (INIS)

Kussmann, Jörg; Luenser, Arne; Beer, Matthias; Ochsenfeld, Christian

2015-01-01

An analytical method to calculate the molecular vibrational Hessian matrix at the self-consistent field level is presented. By analysis of the multipole expansions of the relevant derivatives of Coulomb-type two-electron integral contractions, we show that the effect of the perturbation on the electronic structure due to the displacement of nuclei decays at least as r −2 instead of r −1 . The perturbation is asymptotically local, and the computation of the Hessian matrix can, in principle, be performed with O(N) complexity. Our implementation exhibits linear scaling in all time-determining steps, with some rapid but quadratic-complexity steps remaining. Sample calculations illustrate linear or near-linear scaling in the construction of the complete nuclear Hessian matrix for sparse systems. For more demanding systems, scaling is still considerably sub-quadratic to quadratic, depending on the density of the underlying electronic structure

arXiv On Matrix Factorizations, Residue Pairings and Homological Mirror Symmetry

CERN Document Server

Lerche, Wolfgang

We argue how boundary B-type Landau-Ginzburg models based on matrix factorizations can be used to compute exact superpotentials for intersecting D-brane configurations on compact Calabi-Yau spaces. In this paper, we consider the dependence of open-string, boundary changing correlators on bulk moduli. This determines, via mirror symmetry, non-trivial disk instanton corrections in the A-model. As crucial ingredient we propose a differential equation that involves matrix analogs of Saito's higher residue pairings. As example, we compute from this for the elliptic curve certain quantum products m_2 and m_3, which reproduce genuine boundary changing, open Gromov-Witten invariants.

Storage of sparse files using parallel log-structured file system

Science.gov (United States)

Bent, John M.; Faibish, Sorin; Grider, Gary; Torres, Aaron

2017-11-07

A sparse file is stored without holes by storing a data portion of the sparse file using a parallel log-structured file system; and generating an index entry for the data portion, the index entry comprising a logical offset, physical offset and length of the data portion. The holes can be restored to the sparse file upon a reading of the sparse file. The data portion can be stored at a logical end of the sparse file. Additional storage efficiency can optionally be achieved by (i) detecting a write pattern for a plurality of the data portions and generating a single patterned index entry for the plurality of the patterned data portions; and/or (ii) storing the patterned index entries for a plurality of the sparse files in a single directory, wherein each entry in the single directory comprises an identifier of a corresponding sparse file.

Sparse reconstruction using distribution agnostic bayesian matching pursuit

KAUST Repository

Masood, Mudassir

2013-11-01

A fast matching pursuit method using a Bayesian approach is introduced for sparse signal recovery. This method performs Bayesian estimates of sparse signals even when the signal prior is non-Gaussian or unknown. It is agnostic on signal statistics and utilizes a priori statistics of additive noise and the sparsity rate of the signal, which are shown to be easily estimated from data if not available. The method utilizes a greedy approach and order-recursive updates of its metrics to find the most dominant sparse supports to determine the approximate minimum mean-square error (MMSE) estimate of the sparse signal. Simulation results demonstrate the power and robustness of our proposed estimator. © 2013 IEEE.

Image understanding using sparse representations

CERN Document Server

Thiagarajan, Jayaraman J; Turaga, Pavan; Spanias, Andreas

2014-01-01

Image understanding has been playing an increasingly crucial role in several inverse problems and computer vision. Sparse models form an important component in image understanding, since they emulate the activity of neural receptors in the primary visual cortex of the human brain. Sparse methods have been utilized in several learning problems because of their ability to provide parsimonious, interpretable, and efficient models. Exploiting the sparsity of natural signals has led to advances in several application areas including image compression, denoising, inpainting, compressed sensing, blin

Sparse regularization for force identification using dictionaries

Science.gov (United States)

Qiao, Baijie; Zhang, Xingwu; Wang, Chenxi; Zhang, Hang; Chen, Xuefeng

2016-04-01

The classical function expansion method based on minimizing l2-norm of the response residual employs various basis functions to represent the unknown force. Its difficulty lies in determining the optimum number of basis functions. Considering the sparsity of force in the time domain or in other basis space, we develop a general sparse regularization method based on minimizing l1-norm of the coefficient vector of basis functions. The number of basis functions is adaptively determined by minimizing the number of nonzero components in the coefficient vector during the sparse regularization process. First, according to the profile of the unknown force, the dictionary composed of basis functions is determined. Second, a sparsity convex optimization model for force identification is constructed. Third, given the transfer function and the operational response, Sparse reconstruction by separable approximation (SpaRSA) is developed to solve the sparse regularization problem of force identification. Finally, experiments including identification of impact and harmonic forces are conducted on a cantilever thin plate structure to illustrate the effectiveness and applicability of SpaRSA. Besides the Dirac dictionary, other three sparse dictionaries including Db6 wavelets, Sym4 wavelets and cubic B-spline functions can also accurately identify both the single and double impact forces from highly noisy responses in a sparse representation frame. The discrete cosine functions can also successfully reconstruct the harmonic forces including the sinusoidal, square and triangular forces. Conversely, the traditional Tikhonov regularization method with the L-curve criterion fails to identify both the impact and harmonic forces in these cases.

Sparse inpainting and isotropy

Energy Technology Data Exchange (ETDEWEB)

Feeney, Stephen M.; McEwen, Jason D.; Peiris, Hiranya V. [Department of Physics and Astronomy, University College London, Gower Street, London, WC1E 6BT (United Kingdom); Marinucci, Domenico; Cammarota, Valentina [Department of Mathematics, University of Rome Tor Vergata, via della Ricerca Scientifica 1, Roma, 00133 (Italy); Wandelt, Benjamin D., E-mail: s.feeney@imperial.ac.uk, E-mail: marinucc@axp.mat.uniroma2.it, E-mail: jason.mcewen@ucl.ac.uk, E-mail: h.peiris@ucl.ac.uk, E-mail: wandelt@iap.fr, E-mail: cammarot@axp.mat.uniroma2.it [Kavli Institute for Theoretical Physics, Kohn Hall, University of California, 552 University Road, Santa Barbara, CA, 93106 (United States)

2014-01-01

Sparse inpainting techniques are gaining in popularity as a tool for cosmological data analysis, in particular for handling data which present masked regions and missing observations. We investigate here the relationship between sparse inpainting techniques using the spherical harmonic basis as a dictionary and the isotropy properties of cosmological maps, as for instance those arising from cosmic microwave background (CMB) experiments. In particular, we investigate the possibility that inpainted maps may exhibit anisotropies in the behaviour of higher-order angular polyspectra. We provide analytic computations and simulations of inpainted maps for a Gaussian isotropic model of CMB data, suggesting that the resulting angular trispectrum may exhibit small but non-negligible deviations from isotropy.

A flexible R package for nonnegative matrix factorization

Directory of Open Access Journals (Sweden)

Seoighe Cathal

2010-07-01

Full Text Available Abstract Background Nonnegative Matrix Factorization (NMF is an unsupervised learning technique that has been applied successfully in several fields, including signal processing, face recognition and text mining. Recent applications of NMF in bioinformatics have demonstrated its ability to extract meaningful information from high-dimensional data such as gene expression microarrays. Developments in NMF theory and applications have resulted in a variety of algorithms and methods. However, most NMF implementations have been on commercial platforms, while those that are freely available typically require programming skills. This limits their use by the wider research community. Results Our objective is to provide the bioinformatics community with an open-source, easy-to-use and unified interface to standard NMF algorithms, as well as with a simple framework to help implement and test new NMF methods. For that purpose, we have developed a package for the R/BioConductor platform. The package ports public code to R, and is structured to enable users to easily modify and/or add algorithms. It includes a number of published NMF algorithms and initialization methods and facilitates the combination of these to produce new NMF strategies. Commonly used benchmark data and visualization methods are provided to help in the comparison and interpretation of the results. Conclusions The NMF package helps realize the potential of Nonnegative Matrix Factorization, especially in bioinformatics, providing easy access to methods that have already yielded new insights in many applications. Documentation, source code and sample data are available from CRAN.

Object tracking by occlusion detection via structured sparse learning

KAUST Repository

Zhang, Tianzhu

2013-06-01

Sparse representation based methods have recently drawn much attention in visual tracking due to good performance against illumination variation and occlusion. They assume the errors caused by image variations can be modeled as pixel-wise sparse. However, in many practical scenarios these errors are not truly pixel-wise sparse but rather sparsely distributed in a structured way. In fact, pixels in error constitute contiguous regions within the object\\'s track. This is the case when significant occlusion occurs. To accommodate for non-sparse occlusion in a given frame, we assume that occlusion detected in previous frames can be propagated to the current one. This propagated information determines which pixels will contribute to the sparse representation of the current track. In other words, pixels that were detected as part of an occlusion in the previous frame will be removed from the target representation process. As such, this paper proposes a novel tracking algorithm that models and detects occlusion through structured sparse learning. We test our tracker on challenging benchmark sequences, such as sports videos, which involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that our tracker consistently outperforms the state-of-the-art. © 2013 IEEE.

ℓ2,1 Norm and Hessian Regularized Non-Negative Matrix Factorization with Discriminability for Data Representation

Directory of Open Access Journals (Sweden)

Peng Luo

2017-09-01

Full Text Available Matrix factorization based methods have widely been used in data representation. Among them, Non-negative Matrix Factorization (NMF is a promising technique owing to its psychological and physiological interpretation of spontaneously occurring data. On one hand, although traditional Laplacian regularization can enhance the performance of NMF, it still suffers from the problem of its weak extrapolating ability. On the other hand, standard NMF disregards the discriminative information hidden in the data and cannot guarantee the sparsity of the factor matrices. In this paper, a novel algorithm called ℓ 2 , 1 norm and Hessian Regularized Non-negative Matrix Factorization with Discriminability (ℓ 2 , 1 HNMFD, is developed to overcome the aforementioned problems. In ℓ 2 , 1 HNMFD, Hessian regularization is introduced in the framework of NMF to capture the intrinsic manifold structure of the data. ℓ 2 , 1 norm constraints and approximation orthogonal constraints are added to assure the group sparsity of encoding matrix and characterize the discriminative information of the data simultaneously. To solve the objective function, an efficient optimization scheme is developed to settle it. Our experimental results on five benchmark data sets have demonstrated that ℓ 2 , 1 HNMFD can learn better data representation and provide better clustering results.

Hessian regularization based symmetric nonnegative matrix factorization for clustering gene expression and microbiome data.

Science.gov (United States)

Ma, Yuanyuan; Hu, Xiaohua; He, Tingting; Jiang, Xingpeng

2016-12-01

Nonnegative matrix factorization (NMF) has received considerable attention due to its interpretation of observed samples as combinations of different components, and has been successfully used as a clustering method. As an extension of NMF, Symmetric NMF (SNMF) inherits the advantages of NMF. Unlike NMF, however, SNMF takes a nonnegative similarity matrix as an input, and two lower rank nonnegative matrices (H, H T ) are computed as an output to approximate the original similarity matrix. Laplacian regularization has improved the clustering performance of NMF and SNMF. However, Laplacian regularization (LR), as a classic manifold regularization method, suffers some problems because of its weak extrapolating ability. In this paper, we propose a novel variant of SNMF, called Hessian regularization based symmetric nonnegative matrix factorization (HSNMF), for this purpose. In contrast to Laplacian regularization, Hessian regularization fits the data perfectly and extrapolates nicely to unseen data. We conduct extensive experiments on several datasets including text data, gene expression data and HMP (Human Microbiome Project) data. The results show that the proposed method outperforms other methods, which suggests the potential application of HSNMF in biological data clustering. Copyright © 2016. Published by Elsevier Inc.

Sparse Vector Distributions and Recovery from Compressed Sensing

DEFF Research Database (Denmark)

Sturm, Bob L.

It is well known that the performance of sparse vector recovery algorithms from compressive measurements can depend on the distribution underlying the non-zero elements of a sparse vector. However, the extent of these effects has yet to be explored, and formally presented. In this paper, I...... empirically investigate this dependence for seven distributions and fifteen recovery algorithms. The two morals of this work are: 1) any judgement of the recovery performance of one algorithm over that of another must be prefaced by the conditions for which this is observed to be true, including sparse vector...... distributions, and the criterion for exact recovery; and 2) a recovery algorithm must be selected carefully based on what distribution one expects to underlie the sensed sparse signal....

Yielding physically-interpretable emulators - A Sparse PCA approach

Science.gov (United States)

Galelli, S.; Alsahaf, A.; Giuliani, M.; Castelletti, A.

2015-12-01

Projection-based techniques, such as Principal Orthogonal Decomposition (POD), are a common approach to surrogate high-fidelity process-based models by lower order dynamic emulators. With POD, the dimensionality reduction is achieved by using observations, or 'snapshots' - generated with the high-fidelity model -, to project the entire set of input and state variables of this model onto a smaller set of basis functions that account for most of the variability in the data. While reduction efficiency and variance control of POD techniques are usually very high, the resulting emulators are structurally highly complex and can hardly be given a physically meaningful interpretation as each basis is a projection of the entire set of inputs and states. In this work, we propose a novel approach based on Sparse Principal Component Analysis (SPCA) that combines the several assets of POD methods with the potential for ex-post interpretation of the emulator structure. SPCA reduces the number of non-zero coefficients in the basis functions by identifying a sparse matrix of coefficients. While the resulting set of basis functions may retain less variance of the snapshots, the presence of a few non-zero coefficients assists in the interpretation of the underlying physical processes. The SPCA approach is tested on the reduction of a 1D hydro-ecological model (DYRESM-CAEDYM) used to describe the main ecological and hydrodynamic processes in Tono Dam, Japan. An experimental comparison against a standard POD approach shows that SPCA achieves the same accuracy in emulating a given output variable - for the same level of dimensionality reduction - while yielding better insights of the main process dynamics.

Exhaustive Search for Sparse Variable Selection in Linear Regression

Science.gov (United States)

Igarashi, Yasuhiko; Takenaka, Hikaru; Nakanishi-Ohno, Yoshinori; Uemura, Makoto; Ikeda, Shiro; Okada, Masato

2018-04-01

We propose a K-sparse exhaustive search (ES-K) method and a K-sparse approximate exhaustive search method (AES-K) for selecting variables in linear regression. With these methods, K-sparse combinations of variables are tested exhaustively assuming that the optimal combination of explanatory variables is K-sparse. By collecting the results of exhaustively computing ES-K, various approximate methods for selecting sparse variables can be summarized as density of states. With this density of states, we can compare different methods for selecting sparse variables such as relaxation and sampling. For large problems where the combinatorial explosion of explanatory variables is crucial, the AES-K method enables density of states to be effectively reconstructed by using the replica-exchange Monte Carlo method and the multiple histogram method. Applying the ES-K and AES-K methods to type Ia supernova data, we confirmed the conventional understanding in astronomy when an appropriate K is given beforehand. However, we found the difficulty to determine K from the data. Using virtual measurement and analysis, we argue that this is caused by data shortage.

Sparse Parallel MRI Based on Accelerated Operator Splitting Schemes.

Science.gov (United States)

Cai, Nian; Xie, Weisi; Su, Zhenghang; Wang, Shanshan; Liang, Dong

2016-01-01

Recently, the sparsity which is implicit in MR images has been successfully exploited for fast MR imaging with incomplete acquisitions. In this paper, two novel algorithms are proposed to solve the sparse parallel MR imaging problem, which consists of l 1 regularization and fidelity terms. The two algorithms combine forward-backward operator splitting and Barzilai-Borwein schemes. Theoretically, the presented algorithms overcome the nondifferentiable property in l 1 regularization term. Meanwhile, they are able to treat a general matrix operator that may not be diagonalized by fast Fourier transform and to ensure that a well-conditioned optimization system of equations is simply solved. In addition, we build connections between the proposed algorithms and the state-of-the-art existing methods and prove their convergence with a constant stepsize in Appendix. Numerical results and comparisons with the advanced methods demonstrate the efficiency of proposed algorithms.

Locality constrained joint dynamic sparse representation for local matching based face recognition.

Science.gov (United States)

Wang, Jianzhong; Yi, Yugen; Zhou, Wei; Shi, Yanjiao; Qi, Miao; Zhang, Ming; Zhang, Baoxue; Kong, Jun

2014-01-01

Recently, Sparse Representation-based Classification (SRC) has attracted a lot of attention for its applications to various tasks, especially in biometric techniques such as face recognition. However, factors such as lighting, expression, pose and disguise variations in face images will decrease the performances of SRC and most other face recognition techniques. In order to overcome these limitations, we propose a robust face recognition method named Locality Constrained Joint Dynamic Sparse Representation-based Classification (LCJDSRC) in this paper. In our method, a face image is first partitioned into several smaller sub-images. Then, these sub-images are sparsely represented using the proposed locality constrained joint dynamic sparse representation algorithm. Finally, the representation results for all sub-images are aggregated to obtain the final recognition result. Compared with other algorithms which process each sub-image of a face image independently, the proposed algorithm regards the local matching-based face recognition as a multi-task learning problem. Thus, the latent relationships among the sub-images from the same face image are taken into account. Meanwhile, the locality information of the data is also considered in our algorithm. We evaluate our algorithm by comparing it with other state-of-the-art approaches. Extensive experiments on four benchmark face databases (ORL, Extended YaleB, AR and LFW) demonstrate the effectiveness of LCJDSRC.

Locality constrained joint dynamic sparse representation for local matching based face recognition.

Directory of Open Access Journals (Sweden)

Jianzhong Wang

Full Text Available Recently, Sparse Representation-based Classification (SRC has attracted a lot of attention for its applications to various tasks, especially in biometric techniques such as face recognition. However, factors such as lighting, expression, pose and disguise variations in face images will decrease the performances of SRC and most other face recognition techniques. In order to overcome these limitations, we propose a robust face recognition method named Locality Constrained Joint Dynamic Sparse Representation-based Classification (LCJDSRC in this paper. In our method, a face image is first partitioned into several smaller sub-images. Then, these sub-images are sparsely represented using the proposed locality constrained joint dynamic sparse representation algorithm. Finally, the representation results for all sub-images are aggregated to obtain the final recognition result. Compared with other algorithms which process each sub-image of a face image independently, the proposed algorithm regards the local matching-based face recognition as a multi-task learning problem. Thus, the latent relationships among the sub-images from the same face image are taken into account. Meanwhile, the locality information of the data is also considered in our algorithm. We evaluate our algorithm by comparing it with other state-of-the-art approaches. Extensive experiments on four benchmark face databases (ORL, Extended YaleB, AR and LFW demonstrate the effectiveness of LCJDSRC.

Reprint of "Two-stage sparse coding of region covariance via Log-Euclidean kernels to detect saliency".

Science.gov (United States)

Zhang, Ying-Ying; Yang, Cai; Zhang, Ping

2017-08-01

In this paper, we present a novel bottom-up saliency detection algorithm from the perspective of covariance matrices on a Riemannian manifold. Each superpixel is described by a region covariance matrix on Riemannian Manifolds. We carry out a two-stage sparse coding scheme via Log-Euclidean kernels to extract salient objects efficiently. In the first stage, given background dictionary on image borders, sparse coding of each region covariance via Log-Euclidean kernels is performed. The reconstruction error on the background dictionary is regarded as the initial saliency of each superpixel. In the second stage, an improvement of the initial result is achieved by calculating reconstruction errors of the superpixels on foreground dictionary, which is extracted from the first stage saliency map. The sparse coding in the second stage is similar to the first stage, but is able to effectively highlight the salient objects uniformly from the background. Finally, three post-processing methods-highlight-inhibition function, context-based saliency weighting, and the graph cut-are adopted to further refine the saliency map. Experiments on four public benchmark datasets show that the proposed algorithm outperforms the state-of-the-art methods in terms of precision, recall and mean absolute error, and demonstrate the robustness and efficiency of the proposed method. Copyright © 2017 Elsevier Ltd. All rights reserved.

Compound nucleus in Livsic open-system theory: Factorization of the S matrix

International Nuclear Information System (INIS)

Avishai, Y.

1988-01-01

The compound-nucleus system fits into a mathematical theory of open systems in physics developed by the mathematician M. Livsic [Translations of Mathematical Monographs (American Mathematical Society, Providence, Rhode Island, 1973), Vol. 34]. In this article we review some basic concepts of the above theory and apply it to study the structure of the compound-nucleus S matrix. One of the results is a factorization of the S matrix in the form S(ω) = S +iA/sub k//(tau/sub k/-ω)], where A/sub k/ are known matrices and tau/sub k/ are the complex resonance energies

Dynamic SPECT reconstruction from few projections: a sparsity enforced matrix factorization approach

Science.gov (United States)

Ding, Qiaoqiao; Zan, Yunlong; Huang, Qiu; Zhang, Xiaoqun

2015-02-01

The reconstruction of dynamic images from few projection data is a challenging problem, especially when noise is present and when the dynamic images are vary fast. In this paper, we propose a variational model, sparsity enforced matrix factorization (SEMF), based on low rank matrix factorization of unknown images and enforced sparsity constraints for representing both coefficients and bases. The proposed model is solved via an alternating iterative scheme for which each subproblem is convex and involves the efficient alternating direction method of multipliers (ADMM). The convergence of the overall alternating scheme for the nonconvex problem relies upon the Kurdyka-Łojasiewicz property, recently studied by Attouch et al (2010 Math. Oper. Res. 35 438) and Attouch et al (2013 Math. Program. 137 91). Finally our proof-of-concept simulation on 2D dynamic images shows the advantage of the proposed method compared to conventional methods.

Finding column depedencies in sparse matrices over $ F_ 2 $ by block Wiedemann

NARCIS (Netherlands)

O. Penninga

1998-01-01

textabstractLarge systems of linear equations over $mathbb{F_2$ with sparse coefficient matrices have to be solved as a part of integer factorization with sieve-based methods such as in the Number Field Sieve algorithm. In this report, we first discuss the Wiedemann algorithm to solve these systems

Multichannel Signals Reconstruction Based on Tunable Q-Factor Wavelet Transform-Morphological Component Analysis and Sparse Bayesian Iteration for Rotating Machines

Directory of Open Access Journals (Sweden)

Qing Li

2018-04-01

Full Text Available High-speed remote transmission and large-capacity data storage are difficult issues in signals acquisition of rotating machines condition monitoring. To address these concerns, a novel multichannel signals reconstruction approach based on tunable Q-factor wavelet transform-morphological component analysis (TQWT-MCA and sparse Bayesian iteration algorithm combined with step-impulse dictionary is proposed under the frame of compressed sensing (CS. To begin with, to prevent the periodical impulses loss and effectively separate periodical impulses from the external noise and additive interference components, the TQWT-MCA method is introduced to divide the raw vibration signal into low-resonance component (LRC, i.e., periodical impulses and high-resonance component (HRC, thus, the periodical impulses are preserved effectively. Then, according to the amplitude range of generated LRC, the step-impulse dictionary atom is designed to match the physical structure of periodical impulses. Furthermore, the periodical impulses and HRC are reconstructed by the sparse Bayesian iteration combined with step-impulse dictionary, respectively, finally, the final reconstructed raw signals are obtained by adding the LRC and HRC, meanwhile, the fidelity of the final reconstructed signals is tested by the envelop spectrum and error analysis, respectively. In this work, the proposed algorithm is applied to simulated signal and engineering multichannel signals of a gearbox with multiple faults. Experimental results demonstrate that the proposed approach significantly improves the reconstructive accuracy compared with the state-of-the-art methods such as non-convex Lq (q = 0.5 regularization, spatiotemporal sparse Bayesian learning (SSBL and L1-norm, etc. Additionally, the processing time, i.e., speed of storage and transmission has increased dramatically, more importantly, the fault characteristics of the gearbox with multiple faults are detected and saved, i.e., the

Greedy vs. L1 convex optimization in sparse coding

DEFF Research Database (Denmark)

Ren, Huamin; Pan, Hong; Olsen, Søren Ingvor

2015-01-01

Sparse representation has been applied successfully in many image analysis applications, including abnormal event detection, in which a baseline is to learn a dictionary from the training data and detect anomalies from its sparse codes. During this procedure, sparse codes which can be achieved...... solutions. Considering the property of abnormal event detection, i.e., only normal videos are used as training data due to practical reasons, effective codes in classification application may not perform well in abnormality detection. Therefore, we compare the sparse codes and comprehensively evaluate...... their performance from various aspects to better understand their applicability, including computation time, reconstruction error, sparsity, detection...

Sparse Reconstruction Schemes for Nonlinear Electromagnetic Imaging

KAUST Repository

Desmal, Abdulla

2016-03-01

Electromagnetic imaging is the problem of determining material properties from scattered fields measured away from the domain under investigation. Solving this inverse problem is a challenging task because (i) it is ill-posed due to the presence of (smoothing) integral operators used in the representation of scattered fields in terms of material properties, and scattered fields are obtained at a finite set of points through noisy measurements; and (ii) it is nonlinear simply due the fact that scattered fields are nonlinear functions of the material properties. The work described in this thesis tackles the ill-posedness of the electromagnetic imaging problem using sparsity-based regularization techniques, which assume that the scatterer(s) occupy only a small fraction of the investigation domain. More specifically, four novel imaging methods are formulated and implemented. (i) Sparsity-regularized Born iterative method iteratively linearizes the nonlinear inverse scattering problem and each linear problem is regularized using an improved iterative shrinkage algorithm enforcing the sparsity constraint. (ii) Sparsity-regularized nonlinear inexact Newton method calls for the solution of a linear system involving the Frechet derivative matrix of the forward scattering operator at every iteration step. For faster convergence, the solution of this matrix system is regularized under the sparsity constraint and preconditioned by leveling the matrix singular values. (iii) Sparsity-regularized nonlinear Tikhonov method directly solves the nonlinear minimization problem using Landweber iterations, where a thresholding function is applied at every iteration step to enforce the sparsity constraint. (iv) This last scheme is accelerated using a projected steepest descent method when it is applied to three-dimensional investigation domains. Projection replaces the thresholding operation and enforces the sparsity constraint. Numerical experiments, which are carried out using

Anderson localization through Polyakov loops: Lattice evidence and random matrix model

International Nuclear Information System (INIS)

Bruckmann, Falk; Schierenberg, Sebastian; Kovacs, Tamas G.

2011-01-01

We investigate low-lying fermion modes in SU(2) gauge theory at temperatures above the phase transition. Both staggered and overlap spectra reveal transitions from chaotic (random matrix) to integrable (Poissonian) behavior accompanied by an increasing localization of the eigenmodes. We show that the latter are trapped by local Polyakov loop fluctuations. Islands of such ''wrong'' Polyakov loops can therefore be viewed as defects leading to Anderson localization in gauge theories. We find strong similarities in the spatial profile of these localized staggered and overlap eigenmodes. We discuss possible interpretations of this finding and present a sparse random matrix model that reproduces these features.

Integral transport multiregion geometrical shadowing factor for the approximate collision probability matrix calculation of infinite closely packed lattices

International Nuclear Information System (INIS)

Jowzani-Moghaddam, A.

1981-01-01

An integral transport method of calculating the geometrical shadowing factor in multiregion annular cells for infinite closely packed lattices in cylindrical geometry is developed. This analytical method has been programmed in the TPGS code. This method is based upon a consideration of the properties of the integral transport method for a nonuniform body, which together with Bonalumi's approximations allows the determination of the approximate multiregion collision probability matrix for infinite closely packed lattices with sufficient accuracy. The multiregion geometrical shadowing factors have been calculated for variations in fuel pin annular segment rings in a geometry of annular cells. These shadowing factors can then be used in the calculation of neutron transport from one annulus to another in an infinite lattice. The result of this new geometrical shadowing and collision probability matrix are compared with the Dancoff-Ginsburg correction and the probability matrix using constant shadowing on Yankee fuel elements in an infinite lattice. In these cases the Dancoff-Ginsburg correction factor and collision probability matrix using constant shadowing are in difference by at most 6.2% and 6%, respectively

An in-depth study of sparse codes on abnormality detection

DEFF Research Database (Denmark)

Ren, Huamin; Pan, Hong; Olsen, Søren Ingvor

2016-01-01

Sparse representation has been applied successfully in abnormal event detection, in which the baseline is to learn a dictionary accompanied by sparse codes. While much emphasis is put on discriminative dictionary construction, there are no comparative studies of sparse codes regarding abnormality...... are carried out from various angles to better understand the applicability of sparse codes, including computation time, reconstruction error, sparsity, detection accuracy, and their performance combining various detection methods. The experiment results show that combining OMP codes with maximum coordinate...

Sparse Principal Component Analysis in Medical Shape Modeling

DEFF Research Database (Denmark)

Sjöstrand, Karl; Stegmann, Mikkel Bille; Larsen, Rasmus

2006-01-01

Principal component analysis (PCA) is a widely used tool in medical image analysis for data reduction, model building, and data understanding and exploration. While PCA is a holistic approach where each new variable is a linear combination of all original variables, sparse PCA (SPCA) aims...... analysis in medicine. Results for three different data sets are given in relation to standard PCA and sparse PCA by simple thresholding of sufficiently small loadings. Focus is on a recent algorithm for computing sparse principal components, but a review of other approaches is supplied as well. The SPCA...

Sparse reconstruction using distribution agnostic bayesian matching pursuit

KAUST Repository

Masood, Mudassir; Al-Naffouri, Tareq Y.

2013-01-01

A fast matching pursuit method using a Bayesian approach is introduced for sparse signal recovery. This method performs Bayesian estimates of sparse signals even when the signal prior is non-Gaussian or unknown. It is agnostic on signal statistics

Neighborhood Regularized Logistic Matrix Factorization for Drug-Target Interaction Prediction.

Science.gov (United States)

Liu, Yong; Wu, Min; Miao, Chunyan; Zhao, Peilin; Li, Xiao-Li

2016-02-01

In pharmaceutical sciences, a crucial step of the drug discovery process is the identification of drug-target interactions. However, only a small portion of the drug-target interactions have been experimentally validated, as the experimental validation is laborious and costly. To improve the drug discovery efficiency, there is a great need for the development of accurate computational approaches that can predict potential drug-target interactions to direct the experimental verification. In this paper, we propose a novel drug-target interaction prediction algorithm, namely neighborhood regularized logistic matrix factorization (NRLMF). Specifically, the proposed NRLMF method focuses on modeling the probability that a drug would interact with a target by logistic matrix factorization, where the properties of drugs and targets are represented by drug-specific and target-specific latent vectors, respectively. Moreover, NRLMF assigns higher importance levels to positive observations (i.e., the observed interacting drug-target pairs) than negative observations (i.e., the unknown pairs). Because the positive observations are already experimentally verified, they are usually more trustworthy. Furthermore, the local structure of the drug-target interaction data has also been exploited via neighborhood regularization to achieve better prediction accuracy. We conducted extensive experiments over four benchmark datasets, and NRLMF demonstrated its effectiveness compared with five state-of-the-art approaches.

Beyond cross-domain learning: Multiple-domain nonnegative matrix factorization

KAUST Repository

Wang, Jim Jing-Yan; Gao, Xin

2014-01-01

Traditional cross-domain learning methods transfer learning from a source domain to a target domain. In this paper, we propose the multiple-domain learning problem for several equally treated domains. The multiple-domain learning problem assumes that samples from different domains have different distributions, but share the same feature and class label spaces. Each domain could be a target domain, while also be a source domain for other domains. A novel multiple-domain representation method is proposed for the multiple-domain learning problem. This method is based on nonnegative matrix factorization (NMF), and tries to learn a basis matrix and coding vectors for samples, so that the domain distribution mismatch among different domains will be reduced under an extended variation of the maximum mean discrepancy (MMD) criterion. The novel algorithm - multiple-domain NMF (MDNMF) - was evaluated on two challenging multiple-domain learning problems - multiple user spam email detection and multiple-domain glioma diagnosis. The effectiveness of the proposed algorithm is experimentally verified. © 2013 Elsevier Ltd. All rights reserved.

Beyond cross-domain learning: Multiple-domain nonnegative matrix factorization

KAUST Repository

Wang, Jim Jing-Yan

2014-02-01

Traditional cross-domain learning methods transfer learning from a source domain to a target domain. In this paper, we propose the multiple-domain learning problem for several equally treated domains. The multiple-domain learning problem assumes that samples from different domains have different distributions, but share the same feature and class label spaces. Each domain could be a target domain, while also be a source domain for other domains. A novel multiple-domain representation method is proposed for the multiple-domain learning problem. This method is based on nonnegative matrix factorization (NMF), and tries to learn a basis matrix and coding vectors for samples, so that the domain distribution mismatch among different domains will be reduced under an extended variation of the maximum mean discrepancy (MMD) criterion. The novel algorithm - multiple-domain NMF (MDNMF) - was evaluated on two challenging multiple-domain learning problems - multiple user spam email detection and multiple-domain glioma diagnosis. The effectiveness of the proposed algorithm is experimentally verified. © 2013 Elsevier Ltd. All rights reserved.

Study of electron-molecule collision via finite-element method and r-matrix propagation technique: Exact exchange

International Nuclear Information System (INIS)

Abdolsalami, F.; Abdolsalami, M.; Perez, L.; Gomez, P.

1995-01-01

The authors have applied the finite-element method to electron-molecule collision with the exchange effect implemented rigorously. All the calculations are done in the body-frame within the fixed-nuclei approximation, where the exact treatment of exchange as a nonlocal effect results in a set of coupled integro-differential equations. The method is applied to e-H 2 and e-N 2 scatterings and the cross sections obtained are in very good agreement with the corresponding results the authors have generated from the linear-algebraic approach. This confirms the significant difference observed between their results generated by linear-algebraic method and the previously published e-N 2 cross sections. Their studies show that the finite-element method is clearly superior to the linear-algebraic approach in both memory usage and CPU time especially for large systems such as e-N 2 . The system coefficient matrix obtained from the finite-element method is often sparse and smaller in size by a factor of 12 to 16, compared to the linear-algebraic technique. Moreover, the CPU time required to obtain stable results with the finite-element method is significantly smaller than the linear-algebraic approach for one incident electron energy. The usage of computer resources in the finite-element method can even be reduced much further when (1) scattering calculations involving multiple electron energies are performed in one computer run and (2) exchange, which is a short range effect, is approximated by a sparse matrix. 17 refs., 7 figs., 5 tabs

Multiplicative algorithms for constrained non-negative matrix factorization

KAUST Repository

Peng, Chengbin

2012-12-01

Non-negative matrix factorization (NMF) provides the advantage of parts-based data representation through additive only combinations. It has been widely adopted in areas like item recommending, text mining, data clustering, speech denoising, etc. In this paper, we provide an algorithm that allows the factorization to have linear or approximatly linear constraints with respect to each factor. We prove that if the constraint function is linear, algorithms within our multiplicative framework will converge. This theory supports a large variety of equality and inequality constraints, and can facilitate application of NMF to a much larger domain. Taking the recommender system as an example, we demonstrate how a specialized weighted and constrained NMF algorithm can be developed to fit exactly for the problem, and the tests justify that our constraints improve the performance for both weighted and unweighted NMF algorithms under several different metrics. In particular, on the Movielens data with 94% of items, the Constrained NMF improves recall rate 3% compared to SVD50 and 45% compared to SVD150, which were reported as the best two in the top-N metric. © 2012 IEEE.

Numerical solution of large sparse linear systems

International Nuclear Information System (INIS)

Meurant, Gerard; Golub, Gene.

1982-02-01

This note is based on one of the lectures given at the 1980 CEA-EDF-INRIA Numerical Analysis Summer School whose aim is the study of large sparse linear systems. The main topics are solving least squares problems by orthogonal transformation, fast Poisson solvers and solution of sparse linear system by iterative methods with a special emphasis on preconditioned conjuguate gradient method [fr

Sparse Bayesian Learning for DOA Estimation with Mutual Coupling

Directory of Open Access Journals (Sweden)

Jisheng Dai

2015-10-01

Full Text Available Sparse Bayesian learning (SBL has given renewed interest to the problem of direction-of-arrival (DOA estimation. It is generally assumed that the measurement matrix in SBL is precisely known. Unfortunately, this assumption may be invalid in practice due to the imperfect manifold caused by unknown or misspecified mutual coupling. This paper describes a modified SBL method for joint estimation of DOAs and mutual coupling coefficients with uniform linear arrays (ULAs. Unlike the existing method that only uses stationary priors, our new approach utilizes a hierarchical form of the Student t prior to enforce the sparsity of the unknown signal more heavily. We also provide a distinct Bayesian inference for the expectation-maximization (EM algorithm, which can update the mutual coupling coefficients more efficiently. Another difference is that our method uses an additional singular value decomposition (SVD to reduce the computational complexity of the signal reconstruction process and the sensitivity to the measurement noise.

Indexing amyloid peptide diffraction from serial femtosecond crystallography: new algorithms for sparse patterns

Energy Technology Data Exchange (ETDEWEB)

Brewster, Aaron S. [Lawrence Berkeley National Laboratory, Berkeley, CA 94720 (United States); Sawaya, Michael R. [University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); Rodriguez, Jose [University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); Hattne, Johan; Echols, Nathaniel [Lawrence Berkeley National Laboratory, Berkeley, CA 94720 (United States); McFarlane, Heather T. [University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); Cascio, Duilio [University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); Adams, Paul D. [Lawrence Berkeley National Laboratory, Berkeley, CA 94720 (United States); University of California, Berkeley, CA 94720 (United States); Eisenberg, David S. [University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); University of California, Los Angeles, CA 90095-1570 (United States); Sauter, Nicholas K., E-mail: nksauter@lbl.gov [Lawrence Berkeley National Laboratory, Berkeley, CA 94720 (United States)

2015-02-01

Special methods are required to interpret sparse diffraction patterns collected from peptide crystals at X-ray free-electron lasers. Bragg spots can be indexed from composite-image powder rings, with crystal orientations then deduced from a very limited number of spot positions. Still diffraction patterns from peptide nanocrystals with small unit cells are challenging to index using conventional methods owing to the limited number of spots and the lack of crystal orientation information for individual images. New indexing algorithms have been developed as part of the Computational Crystallography Toolbox (cctbx) to overcome these challenges. Accurate unit-cell information derived from an aggregate data set from thousands of diffraction patterns can be used to determine a crystal orientation matrix for individual images with as few as five reflections. These algorithms are potentially applicable not only to amyloid peptides but also to any set of diffraction patterns with sparse properties, such as low-resolution virus structures or high-throughput screening of still images captured by raster-scanning at synchrotron sources. As a proof of concept for this technique, successful integration of X-ray free-electron laser (XFEL) data to 2.5 Å resolution for the amyloid segment GNNQQNY from the Sup35 yeast prion is presented.

Sparse Source EEG Imaging with the Variational Garrote

DEFF Research Database (Denmark)

Hansen, Sofie Therese; Stahlhut, Carsten; Hansen, Lars Kai

2013-01-01

EEG imaging, the estimation of the cortical source distribution from scalp electrode measurements, poses an extremely ill-posed inverse problem. Recent work by Delorme et al. (2012) supports the hypothesis that distributed source solutions are sparse. We show that direct search for sparse solutions...

Low-count PET image restoration using sparse representation

Science.gov (United States)

Li, Tao; Jiang, Changhui; Gao, Juan; Yang, Yongfeng; Liang, Dong; Liu, Xin; Zheng, Hairong; Hu, Zhanli

2018-04-01

In the field of positron emission tomography (PET), reconstructed images are often blurry and contain noise. These problems are primarily caused by the low resolution of projection data. Solving this problem by improving hardware is an expensive solution, and therefore, we attempted to develop a solution based on optimizing several related algorithms in both the reconstruction and image post-processing domains. As sparse technology is widely used, sparse prediction is increasingly applied to solve this problem. In this paper, we propose a new sparse method to process low-resolution PET images. Two dictionaries (D1 for low-resolution PET images and D2 for high-resolution PET images) are learned from a group real PET image data sets. Among these two dictionaries, D1 is used to obtain a sparse representation for each patch of the input PET image. Then, a high-resolution PET image is generated from this sparse representation using D2. Experimental results indicate that the proposed method exhibits a stable and superior ability to enhance image resolution and recover image details. Quantitatively, this method achieves better performance than traditional methods. This proposed strategy is a new and efficient approach for improving the quality of PET images.

X-ray computed tomography using curvelet sparse regularization.

Science.gov (United States)

Wieczorek, Matthias; Frikel, Jürgen; Vogel, Jakob; Eggl, Elena; Kopp, Felix; Noël, Peter B; Pfeiffer, Franz; Demaret, Laurent; Lasser, Tobias

2015-04-01

Reconstruction of x-ray computed tomography (CT) data remains a mathematically challenging problem in medical imaging. Complementing the standard analytical reconstruction methods, sparse regularization is growing in importance, as it allows inclusion of prior knowledge. The paper presents a method for sparse regularization based on the curvelet frame for the application to iterative reconstruction in x-ray computed tomography. In this work, the authors present an iterative reconstruction approach based on the alternating direction method of multipliers using curvelet sparse regularization. Evaluation of the method is performed on a specifically crafted numerical phantom dataset to highlight the method's strengths. Additional evaluation is performed on two real datasets from commercial scanners with different noise characteristics, a clinical bone sample acquired in a micro-CT and a human abdomen scanned in a diagnostic CT. The results clearly illustrate that curvelet sparse regularization has characteristic strengths. In particular, it improves the restoration and resolution of highly directional, high contrast features with smooth contrast variations. The authors also compare this approach to the popular technique of total variation and to traditional filtered backprojection. The authors conclude that curvelet sparse regularization is able to improve reconstruction quality by reducing noise while preserving highly directional features.

Polychoric/Tetrachoric Matrix or Pearson Matrix? A methodological study

Directory of Open Access Journals (Sweden)

Dominguez Lara, Sergio Alexis

2014-04-01

Full Text Available The use of product-moment correlation of Pearson is common in most studies in factor analysis in psychology, but it is known that this statistic is only applicable when the variables related are in interval scale and normally distributed, and when are used in ordinal data may to produce a distorted correlation matrix . Thus is a suitable option using polychoric/tetrachoric matrices in item-level factor analysis when the items are in level measurement nominal or ordinal. The aim of this study was to show the differences in the KMO, Bartlett`s Test and Determinant of the Matrix, percentage of variance explained and factor loadings in depression trait scale of Depression Inventory Trait - State and the Neuroticism dimension of the short form of the Eysenck Personality Questionnaire -Revised, regarding the use of matrices polychoric/tetrachoric matrices and Pearson. These instruments was analyzed with different extraction methods (Maximum Likelihood, Minimum Rank Factor Analysis, Unweighted Least Squares and Principal Components, keeping constant the rotation method Promin were analyzed. Were observed differences regarding sample adequacy measures, as well as with respect to the explained variance and the factor loadings, for solutions having as polychoric/tetrachoric matrix. So it can be concluded that the polychoric / tetrachoric matrix give better results than Pearson matrices when it comes to item-level factor analysis using different methods.

Identification of Successive ``Unobservable'' Cyber Data Attacks in Power Systems Through Matrix Decomposition

Science.gov (United States)

Gao, Pengzhi; Wang, Meng; Chow, Joe H.; Ghiocel, Scott G.; Fardanesh, Bruce; Stefopoulos, George; Razanousky, Michael P.

2016-11-01

This paper presents a new framework of identifying a series of cyber data attacks on power system synchrophasor measurements. We focus on detecting "unobservable" cyber data attacks that cannot be detected by any existing method that purely relies on measurements received at one time instant. Leveraging the approximate low-rank property of phasor measurement unit (PMU) data, we formulate the identification problem of successive unobservable cyber attacks as a matrix decomposition problem of a low-rank matrix plus a transformed column-sparse matrix. We propose a convex-optimization-based method and provide its theoretical guarantee in the data identification. Numerical experiments on actual PMU data from the Central New York power system and synthetic data are conducted to verify the effectiveness of the proposed method.

Microstructure Images Restoration of Metallic Materials Based upon KSVD and Smoothing Penalty Sparse Representation Approach.

Science.gov (United States)

Li, Qing; Liang, Steven Y

2018-04-20

Microstructure images of metallic materials play a significant role in industrial applications. To address image degradation problem of metallic materials, a novel image restoration technique based on K-means singular value decomposition (KSVD) and smoothing penalty sparse representation (SPSR) algorithm is proposed in this work, the microstructure images of aluminum alloy 7075 (AA7075) material are used as examples. To begin with, to reflect the detail structure characteristics of the damaged image, the KSVD dictionary is introduced to substitute the traditional sparse transform basis (TSTB) for sparse representation. Then, due to the image restoration, modeling belongs to a highly underdetermined equation, and traditional sparse reconstruction methods may cause instability and obvious artifacts in the reconstructed images, especially reconstructed image with many smooth regions and the noise level is strong, thus the SPSR (here, q = 0.5) algorithm is designed to reconstruct the damaged image. The results of simulation and two practical cases demonstrate that the proposed method has superior performance compared with some state-of-the-art methods in terms of restoration performance factors and visual quality. Meanwhile, the grain size parameters and grain boundaries of microstructure image are discussed before and after they are restored by proposed method.

An Augmented Incomplete Factorization Approach for Computing the Schur Complement in Stochastic Optimization

KAUST Repository

Petra, Cosmin G.; Schenk, Olaf; Lubin, Miles; Gä ertner, Klaus

2014-01-01

We present a scalable approach and implementation for solving stochastic optimization problems on high-performance computers. In this work we revisit the sparse linear algebra computations of the parallel solver PIPS with the goal of improving the shared-memory performance and decreasing the time to solution. These computations consist of solving sparse linear systems with multiple sparse right-hand sides and are needed in our Schur-complement decomposition approach to compute the contribution of each scenario to the Schur matrix. Our novel approach uses an incomplete augmented factorization implemented within the PARDISO linear solver and an outer BiCGStab iteration to efficiently absorb pivot perturbations occurring during factorization. This approach is capable of both efficiently using the cores inside a computational node and exploiting sparsity of the right-hand sides. We report on the performance of the approach on highperformance computers when solving stochastic unit commitment problems of unprecedented size (billions of variables and constraints) that arise in the optimization and control of electrical power grids. Our numerical experiments suggest that supercomputers can be efficiently used to solve power grid stochastic optimization problems with thousands of scenarios under the strict "real-time" requirements of power grid operators. To our knowledge, this has not been possible prior to the present work. © 2014 Society for Industrial and Applied Mathematics.

Improving temporal resolution in fMRI using a 3D spiral acquisition and low rank plus sparse (L+S) reconstruction.

Science.gov (United States)

Petrov, Andrii Y; Herbst, Michael; Andrew Stenger, V

2017-08-15

Rapid whole-brain dynamic Magnetic Resonance Imaging (MRI) is of particular interest in Blood Oxygen Level Dependent (BOLD) functional MRI (fMRI). Faster acquisitions with higher temporal sampling of the BOLD time-course provide several advantages including increased sensitivity in detecting functional activation, the possibility of filtering out physiological noise for improving temporal SNR, and freezing out head motion. Generally, faster acquisitions require undersampling of the data which results in aliasing artifacts in the object domain. A recently developed low-rank (L) plus sparse (S) matrix decomposition model (L+S) is one of the methods that has been introduced to reconstruct images from undersampled dynamic MRI data. The L+S approach assumes that the dynamic MRI data, represented as a space-time matrix M, is a linear superposition of L and S components, where L represents highly spatially and temporally correlated elements, such as the image background, while S captures dynamic information that is sparse in an appropriate transform domain. This suggests that L+S might be suited for undersampled task or slow event-related fMRI acquisitions because the periodic nature of the BOLD signal is sparse in the temporal Fourier transform domain and slowly varying low-rank brain background signals, such as physiological noise and drift, will be predominantly low-rank. In this work, as a proof of concept, we exploit the L+S method for accelerating block-design fMRI using a 3D stack of spirals (SoS) acquisition where undersampling is performed in the k z -t domain. We examined the feasibility of the L+S method to accurately separate temporally correlated brain background information in the L component while capturing periodic BOLD signals in the S component. We present results acquired in control human volunteers at 3T for both retrospective and prospectively acquired fMRI data for a visual activation block-design task. We show that a SoS fMRI acquisition with an

Sparse dictionary for synthetic transmit aperture medical ultrasound imaging.

Science.gov (United States)

Wang, Ping; Jiang, Jin-Yang; Li, Na; Luo, Han-Wu; Li, Fang; Cui, Shi-Gang

2017-07-01

It is possible to recover a signal below the Nyquist sampling limit using a compressive sensing technique in ultrasound imaging. However, the reconstruction enabled by common sparse transform approaches does not achieve satisfactory results. Considering the ultrasound echo signal's features of attenuation, repetition, and superposition, a sparse dictionary with the emission pulse signal is proposed. Sparse coefficients in the proposed dictionary have high sparsity. Images reconstructed with this dictionary were compared with those obtained with the three other common transforms, namely, discrete Fourier transform, discrete cosine transform, and discrete wavelet transform. The performance of the proposed dictionary was analyzed via a simulation and experimental data. The mean absolute error (MAE) was used to quantify the quality of the reconstructions. Experimental results indicate that the MAE associated with the proposed dictionary was always the smallest, the reconstruction time required was the shortest, and the lateral resolution and contrast of the reconstructed images were also the closest to the original images. The proposed sparse dictionary performed better than the other three sparse transforms. With the same sampling rate, the proposed dictionary achieved excellent reconstruction quality.

A sparse electromagnetic imaging scheme using nonlinear landweber iterations

KAUST Repository

Desmal, Abdulla; Bagci, Hakan

2015-01-01

Development and use of electromagnetic inverse scattering techniques for imagining sparse domains have been on the rise following the recent advancements in solving sparse optimization problems. Existing techniques rely on iteratively converting

Local posterior concentration rate for multilevel sparse sequences

NARCIS (Netherlands)

Belitser, E.N.; Nurushev, N.

2017-01-01

We consider empirical Bayesian inference in the many normal means model in the situation when the high-dimensional mean vector is multilevel sparse, that is,most of the entries of the parameter vector are some fixed values. For instance, the traditional sparse signal is a particular case (with one

Analog system for computing sparse codes

Science.gov (United States)

Rozell, Christopher John; Johnson, Don Herrick; Baraniuk, Richard Gordon; Olshausen, Bruno A.; Ortman, Robert Lowell

2010-08-24

A parallel dynamical system for computing sparse representations of data, i.e., where the data can be fully represented in terms of a small number of non-zero code elements, and for reconstructing compressively sensed images. The system is based on the principles of thresholding and local competition that solves a family of sparse approximation problems corresponding to various sparsity metrics. The system utilizes Locally Competitive Algorithms (LCAs), nodes in a population continually compete with neighboring units using (usually one-way) lateral inhibition to calculate coefficients representing an input in an over complete dictionary.

A Transfer Learning Approach for Applying Matrix Factorization to Small ITS Datasets

Science.gov (United States)

Voß, Lydia; Schatten, Carlotta; Mazziotti, Claudia; Schmidt-Thieme, Lars

2015-01-01

Machine Learning methods for Performance Prediction in Intelligent Tutoring Systems (ITS) have proven their efficacy; specific methods, e.g. Matrix Factorization (MF), however suffer from the lack of available information about new tasks or new students. In this paper we show how this problem could be solved by applying Transfer Learning (TL),…

Energy Scaling Advantages of Resistive Memory Crossbar Based Computation and its Application to Sparse Coding

Directory of Open Access Journals (Sweden)

Sapan eAgarwal

2016-01-01

Full Text Available The exponential increase in data over the last decade presents a significant challenge to analytics efforts that seek to process and interpret such data for various applications. Neural-inspired computing approaches are being developed in order to leverage the computational advantages of the analog, low-power data processing observed in biological systems. Analog resistive memory crossbars can perform a parallel read or a vector-matrix multiplication as well as a parallel write or a rank-1 update with high computational efficiency. For an NxN crossbar, these two kernels are at a minimum O(N more energy efficient than a digital memory-based architecture. If the read operation is noise limited, the energy to read a column can be independent of the crossbar size (O(1. These two kernels form the basis of many neuromorphic algorithms such as image, text, and speech recognition. For instance, these kernels can be applied to a neural sparse coding algorithm to give an O(N reduction in energy for the entire algorithm. Sparse coding is a rich problem with a host of applications including computer vision, object tracking, and more generally unsupervised learning.

Efficient Pseudorecursive Evaluation Schemes for Non-adaptive Sparse Grids

KAUST Repository

Buse, Gerrit; Pflü ger, Dirk; Jacob, Riko

2014-01-01

In this work we propose novel algorithms for storing and evaluating sparse grid functions, operating on regular (not spatially adaptive), yet potentially dimensionally adaptive grid types. Besides regular sparse grids our approach includes truncated

Sparse PCA, a new method for unsupervised analyses of fMRI data

DEFF Research Database (Denmark)

Sjöstrand, Karl; Lund, Torben E.; Madsen, Kristoffer Hougaard

2006-01-01

favorable circumstances, one of more of these signals describe activation patterns, while others model noise and other nuisance factors. This work introduces a competing method for fMRI analysis known as sparse principal component analysis (SPCA). We argue that SPCA is less committed than ICA and show...... that similar results, with better suppression of noise, are obtained....

Comparison between sparsely distributed memory and Hopfield-type neural network models

Science.gov (United States)

Keeler, James D.

1986-01-01

The Sparsely Distributed Memory (SDM) model (Kanerva, 1984) is compared to Hopfield-type neural-network models. A mathematical framework for comparing the two is developed, and the capacity of each model is investigated. The capacity of the SDM can be increased independently of the dimension of the stored vectors, whereas the Hopfield capacity is limited to a fraction of this dimension. However, the total number of stored bits per matrix element is the same in the two models, as well as for extended models with higher order interactions. The models are also compared in their ability to store sequences of patterns. The SDM is extended to include time delays so that contextual information can be used to cover sequences. Finally, it is shown how a generalization of the SDM allows storage of correlated input pattern vectors.

Occlusion detection via structured sparse learning for robust object tracking

KAUST Repository

Zhang, Tianzhu

2014-01-01

Sparse representation based methods have recently drawn much attention in visual tracking due to good performance against illumination variation and occlusion. They assume the errors caused by image variations can be modeled as pixel-wise sparse. However, in many practical scenarios, these errors are not truly pixel-wise sparse but rather sparsely distributed in a structured way. In fact, pixels in error constitute contiguous regions within the object’s track. This is the case when significant occlusion occurs. To accommodate for nonsparse occlusion in a given frame, we assume that occlusion detected in previous frames can be propagated to the current one. This propagated information determines which pixels will contribute to the sparse representation of the current track. In other words, pixels that were detected as part of an occlusion in the previous frame will be removed from the target representation process. As such, this paper proposes a novel tracking algorithm that models and detects occlusion through structured sparse learning. We test our tracker on challenging benchmark sequences, such as sports videos, which involve heavy occlusion, drastic illumination changes, and large pose variations. Extensive experimental results show that our proposed tracker consistently outperforms the state-of-the-art trackers.

Sparse Representation Based SAR Vehicle Recognition along with Aspect Angle

Directory of Open Access Journals (Sweden)

Xiangwei Xing

2014-01-01

Full Text Available As a method of representing the test sample with few training samples from an overcomplete dictionary, sparse representation classification (SRC has attracted much attention in synthetic aperture radar (SAR automatic target recognition (ATR recently. In this paper, we develop a novel SAR vehicle recognition method based on sparse representation classification along with aspect information (SRCA, in which the correlation between the vehicle’s aspect angle and the sparse representation vector is exploited. The detailed procedure presented in this paper can be summarized as follows. Initially, the sparse representation vector of a test sample is solved by sparse representation algorithm with a principle component analysis (PCA feature-based dictionary. Then, the coefficient vector is projected onto a sparser one within a certain range of the vehicle’s aspect angle. Finally, the vehicle is classified into a certain category that minimizes the reconstruction error with the novel sparse representation vector. Extensive experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR dataset and the results demonstrate that the proposed method performs robustly under the variations of depression angle and target configurations, as well as incomplete observation.

Positive semidefinite tensor factorizations of the two-electron integral matrix for low-scaling ab initio electronic structure.

Science.gov (United States)

Hoy, Erik P; Mazziotti, David A

2015-08-14

Tensor factorization of the 2-electron integral matrix is a well-known technique for reducing the computational scaling of ab initio electronic structure methods toward that of Hartree-Fock and density functional theories. The simplest factorization that maintains the positive semidefinite character of the 2-electron integral matrix is the Cholesky factorization. In this paper, we introduce a family of positive semidefinite factorizations that generalize the Cholesky factorization. Using an implementation of the factorization within the parametric 2-RDM method [D. A. Mazziotti, Phys. Rev. Lett. 101, 253002 (2008)], we study several inorganic molecules, alkane chains, and potential energy curves and find that this generalized factorization retains the accuracy and size extensivity of the Cholesky factorization, even in the presence of multi-reference correlation. The generalized family of positive semidefinite factorizations has potential applications to low-scaling ab initio electronic structure methods that treat electron correlation with a computational cost approaching that of the Hartree-Fock method or density functional theory.

Positive semidefinite tensor factorizations of the two-electron integral matrix for low-scaling ab initio electronic structure

Energy Technology Data Exchange (ETDEWEB)

Hoy, Erik P.; Mazziotti, David A., E-mail: damazz@uchicago.edu [Department of Chemistry and The James Franck Institute, The University of Chicago, Chicago, Illinois 60637 (United States)

2015-08-14

Tensor factorization of the 2-electron integral matrix is a well-known technique for reducing the computational scaling of ab initio electronic structure methods toward that of Hartree-Fock and density functional theories. The simplest factorization that maintains the positive semidefinite character of the 2-electron integral matrix is the Cholesky factorization. In this paper, we introduce a family of positive semidefinite factorizations that generalize the Cholesky factorization. Using an implementation of the factorization within the parametric 2-RDM method [D. A. Mazziotti, Phys. Rev. Lett. 101, 253002 (2008)], we study several inorganic molecules, alkane chains, and potential energy curves and find that this generalized factorization retains the accuracy and size extensivity of the Cholesky factorization, even in the presence of multi-reference correlation. The generalized family of positive semidefinite factorizations has potential applications to low-scaling ab initio electronic structure methods that treat electron correlation with a computational cost approaching that of the Hartree-Fock method or density functional theory.

Learning sparse generative models of audiovisual signals

OpenAIRE

Monaci, Gianluca; Sommer, Friedrich T.; Vandergheynst, Pierre

2008-01-01

This paper presents a novel framework to learn sparse represen- tations for audiovisual signals. An audiovisual signal is modeled as a sparse sum of audiovisual kernels. The kernels are bimodal functions made of synchronous audio and video components that can be positioned independently and arbitrarily in space and time. We design an algorithm capable of learning sets of such audiovi- sual, synchronous, shift-invariant functions by alternatingly solving a coding and a learning pr...

Support agnostic Bayesian matching pursuit for block sparse signals

KAUST Repository

Masood, Mudassir

2013-05-01

A fast matching pursuit method using a Bayesian approach is introduced for block-sparse signal recovery. This method performs Bayesian estimates of block-sparse signals even when the distribution of active blocks is non-Gaussian or unknown. It is agnostic to the distribution of active blocks in the signal and utilizes a priori statistics of additive noise and the sparsity rate of the signal, which are shown to be easily estimated from data and no user intervention is required. The method requires a priori knowledge of block partition and utilizes a greedy approach and order-recursive updates of its metrics to find the most dominant sparse supports to determine the approximate minimum mean square error (MMSE) estimate of the block-sparse signal. Simulation results demonstrate the power and robustness of our proposed estimator. © 2013 IEEE.

Preconditioned Inexact Newton for Nonlinear Sparse Electromagnetic Imaging

KAUST Repository

Desmal, Abdulla

2014-05-04

Newton-type algorithms have been extensively studied in nonlinear microwave imaging due to their quadratic convergence rate and ability to recover images with high contrast values. In the past, Newton methods have been implemented in conjunction with smoothness promoting optimization/regularization schemes. However, this type of regularization schemes are known to perform poorly when applied in imagining domains with sparse content or sharp variations. In this work, an inexact Newton algorithm is formulated and implemented in conjunction with a linear sparse optimization scheme. A novel preconditioning technique is proposed to increase the convergence rate of the optimization problem. Numerical results demonstrate that the proposed framework produces sharper and more accurate images when applied in sparse/sparsified domains.

Preconditioned Inexact Newton for Nonlinear Sparse Electromagnetic Imaging

KAUST Repository

Desmal, Abdulla

2014-01-06

Newton-type algorithms have been extensively studied in nonlinear microwave imaging due to their quadratic convergence rate and ability to recover images with high contrast values. In the past, Newton methods have been implemented in conjunction with smoothness promoting optimization/regularization schemes. However, this type of regularization schemes are known to perform poorly when applied in imagining domains with sparse content or sharp variations. In this work, an inexact Newton algorithm is formulated and implemented in conjunction with a linear sparse optimization scheme. A novel preconditioning technique is proposed to increase the convergence rate of the optimization problem. Numerical results demonstrate that the proposed framework produces sharper and more accurate images when applied in sparse/sparsified domains.

Electromagnetic Formation Flight (EMFF) for Sparse Aperture Arrays

Science.gov (United States)

Kwon, Daniel W.; Miller, David W.; Sedwick, Raymond J.

2004-01-01

Traditional methods of actuating spacecraft in sparse aperture arrays use propellant as a reaction mass. For formation flying systems, propellant becomes a critical consumable which can be quickly exhausted while maintaining relative orientation. Additional problems posed by propellant include optical contamination, plume impingement, thermal emission, and vibration excitation. For these missions where control of relative degrees of freedom is important, we consider using a system of electromagnets, in concert with reaction wheels, to replace the consumables. Electromagnetic Formation Flight sparse apertures, powered by solar energy, are designed differently from traditional propulsion systems, which are based on V. This paper investigates the design of sparse apertures both inside and outside the Earth's gravity field.

Preconditioned Inexact Newton for Nonlinear Sparse Electromagnetic Imaging

KAUST Repository

Desmal, Abdulla; Bagci, Hakan

2014-01-01

Newton-type algorithms have been extensively studied in nonlinear microwave imaging due to their quadratic convergence rate and ability to recover images with high contrast values. In the past, Newton methods have been implemented in conjunction with smoothness promoting optimization/regularization schemes. However, this type of regularization schemes are known to perform poorly when applied in imagining domains with sparse content or sharp variations. In this work, an inexact Newton algorithm is formulated and implemented in conjunction with a linear sparse optimization scheme. A novel preconditioning technique is proposed to increase the convergence rate of the optimization problem. Numerical results demonstrate that the proposed framework produces sharper and more accurate images when applied in sparse/sparsified domains.

A comprehensive study of sparse codes on abnormality detection

DEFF Research Database (Denmark)

Ren, Huamin; Pan, Hong; Olsen, Søren Ingvor

2017-01-01

Sparse representation has been applied successfully in abnor-mal event detection, in which the baseline is to learn a dic-tionary accompanied by sparse codes. While much empha-sis is put on discriminative dictionary construction, there areno comparative studies of sparse codes regarding abnormal-ity...... detection. We comprehensively study two types of sparsecodes solutions - greedy algorithms and convex L1-norm so-lutions - and their impact on abnormality detection perfor-mance. We also propose our framework of combining sparsecodes with different detection methods. Our comparative ex-periments are carried...

Support agnostic Bayesian matching pursuit for block sparse signals

KAUST Repository

Masood, Mudassir; Al-Naffouri, Tareq Y.

2013-01-01

priori knowledge of block partition and utilizes a greedy approach and order-recursive updates of its metrics to find the most dominant sparse supports to determine the approximate minimum mean square error (MMSE) estimate of the block-sparse signal

Matrix Factorisation-based Calibration For Air Quality Crowd-sensing

Science.gov (United States)

Dorffer, Clement; Puigt, Matthieu; Delmaire, Gilles; Roussel, Gilles; Rouvoy, Romain; Sagnier, Isabelle

2017-04-01

sensors share some information using the APISENSE® crowdsensing platform and we aim to calibrate the sensor responses from the data directly. For that purpose, we express the sensor readings as a low-rank matrix with missing entries and we revisit self-calibration as a Matrix Factorization (MF) problem. In our proposed framework, one factor matrix contains the calibration parameters while the other is structured by the calibration model and contains some values of the sensed phenomenon. The MF calibration approach also uses the precise measurements from ATMO—the French public institution—to drive the calibration of the mobile sensors. MF calibration can be improved using, e.g., the mean calibration parameters provided by the sensor manufacturers, or using sparse priors or a model of the physical phenomenon. All our approaches are shown to provide a better calibration accuracy than matrix-completion-based and robust-regression-based methods, even in difficult scenarios involving a lot of missing data and/or very few accurate references. When combined with a dictionary of air quality patterns, our experiments suggest that MF is not only able to perform sensor network calibration but also to provide detailed maps of air quality.

Selectivity and sparseness in randomly connected balanced networks.

Directory of Open Access Journals (Sweden)

Cengiz Pehlevan

Full Text Available Neurons in sensory cortex show stimulus selectivity and sparse population response, even in cases where no strong functionally specific structure in connectivity can be detected. This raises the question whether selectivity and sparseness can be generated and maintained in randomly connected networks. We consider a recurrent network of excitatory and inhibitory spiking neurons with random connectivity, driven by random projections from an input layer of stimulus selective neurons. In this architecture, the stimulus-to-stimulus and neuron-to-neuron modulation of total synaptic input is weak compared to the mean input. Surprisingly, we show that in the balanced state the network can still support high stimulus selectivity and sparse population response. In the balanced state, strong synapses amplify the variation in synaptic input and recurrent inhibition cancels the mean. Functional specificity in connectivity emerges due to the inhomogeneity caused by the generative statistical rule used to build the network. We further elucidate the mechanism behind and evaluate the effects of model parameters on population sparseness and stimulus selectivity. Network response to mixtures of stimuli is investigated. It is shown that a balanced state with unselective inhibition can be achieved with densely connected input to inhibitory population. Balanced networks exhibit the "paradoxical" effect: an increase in excitatory drive to inhibition leads to decreased inhibitory population firing rate. We compare and contrast selectivity and sparseness generated by the balanced network to randomly connected unbalanced networks. Finally, we discuss our results in light of experiments.

SPARSE ELECTROMAGNETIC IMAGING USING NONLINEAR LANDWEBER ITERATIONS

KAUST Repository

Desmal, Abdulla

2015-07-29

A scheme for efficiently solving the nonlinear electromagnetic inverse scattering problem on sparse investigation domains is described. The proposed scheme reconstructs the (complex) dielectric permittivity of an investigation domain from fields measured away from the domain itself. Least-squares data misfit between the computed scattered fields, which are expressed as a nonlinear function of the permittivity, and the measured fields is constrained by the L0/L1-norm of the solution. The resulting minimization problem is solved using nonlinear Landweber iterations, where at each iteration a thresholding function is applied to enforce the sparseness-promoting L0/L1-norm constraint. The thresholded nonlinear Landweber iterations are applied to several two-dimensional problems, where the ``measured\\'\\' fields are synthetically generated or obtained from actual experiments. These numerical experiments demonstrate the accuracy, efficiency, and applicability of the proposed scheme in reconstructing sparse profiles with high permittivity values.

Sparse tensor spherical harmonics approximation in radiative transfer

International Nuclear Information System (INIS)

Grella, K.; Schwab, Ch.

2011-01-01

The stationary monochromatic radiative transfer equation is a partial differential transport equation stated on a five-dimensional phase space. To obtain a well-posed problem, boundary conditions have to be prescribed on the inflow part of the domain boundary. We solve the equation with a multi-level Galerkin FEM in physical space and a spectral discretization with harmonics in solid angle and show that the benefits of the concept of sparse tensor products, known from the context of sparse grids, can also be leveraged in combination with a spectral discretization. Our method allows us to include high spectral orders without incurring the 'curse of dimension' of a five-dimensional computational domain. Neglecting boundary conditions, we find analytically that for smooth solutions, the convergence rate of the full tensor product method is retained in our method up to a logarithmic factor, while the number of degrees of freedom grows essentially only as fast as for the purely spatial problem. For the case with boundary conditions, we propose a splitting of the physical function space and a conforming tensorization. Numerical experiments in two physical and one angular dimension show evidence for the theoretical convergence rates to hold in the latter case as well.

Sparse Bayesian Learning for Nonstationary Data Sources

Science.gov (United States)

Fujimaki, Ryohei; Yairi, Takehisa; Machida, Kazuo

This paper proposes an online Sparse Bayesian Learning (SBL) algorithm for modeling nonstationary data sources. Although most learning algorithms implicitly assume that a data source does not change over time (stationary), one in the real world usually does due to such various factors as dynamically changing environments, device degradation, sudden failures, etc (nonstationary). The proposed algorithm can be made useable for stationary online SBL by setting time decay parameters to zero, and as such it can be interpreted as a single unified framework for online SBL for use with stationary and nonstationary data sources. Tests both on four types of benchmark problems and on actual stock price data have shown it to perform well.

Factorizations of rational matrix functions with application to discrete isomonodromic transformations and difference Painleve equations

International Nuclear Information System (INIS)

Dzhamay, Anton

2009-01-01

We study factorizations of rational matrix functions with simple poles on the Riemann sphere. For the quadratic case (two poles) we show, using multiplicative representations of such matrix functions, that a good coordinate system on this space is given by a mix of residue eigenvectors of the matrix and its inverse. Our approach is motivated by the theory of discrete isomonodromic transformations and their relationship with difference Painleve equations. In particular, in these coordinates, basic isomonodromic transformations take the form of the discrete Euler-Lagrange equations. Secondly we show that dPV equations, previously obtained in this context by D Arinkin and A Borodin, can be understood as simple relationships between the residues of such matrices and their inverses.

Structure-based bayesian sparse reconstruction

KAUST Repository

Quadeer, Ahmed Abdul; Al-Naffouri, Tareq Y.

2012-01-01

Sparse signal reconstruction algorithms have attracted research attention due to their wide applications in various fields. In this paper, we present a simple Bayesian approach that utilizes the sparsity constraint and a priori statistical

Binary Sparse Phase Retrieval via Simulated Annealing

Directory of Open Access Journals (Sweden)

Wei Peng

2016-01-01

Full Text Available This paper presents the Simulated Annealing Sparse PhAse Recovery (SASPAR algorithm for reconstructing sparse binary signals from their phaseless magnitudes of the Fourier transform. The greedy strategy version is also proposed for a comparison, which is a parameter-free algorithm. Sufficient numeric simulations indicate that our method is quite effective and suggest the binary model is robust. The SASPAR algorithm seems competitive to the existing methods for its efficiency and high recovery rate even with fewer Fourier measurements.

A Modified Sparse Representation Method for Facial Expression Recognition

Directory of Open Access Journals (Sweden)

Wei Wang

2016-01-01

Full Text Available In this paper, we carry on research on a facial expression recognition method, which is based on modified sparse representation recognition (MSRR method. On the first stage, we use Haar-like+LPP to extract feature and reduce dimension. On the second stage, we adopt LC-K-SVD (Label Consistent K-SVD method to train the dictionary, instead of adopting directly the dictionary from samples, and add block dictionary training into the training process. On the third stage, stOMP (stagewise orthogonal matching pursuit method is used to speed up the convergence of OMP (orthogonal matching pursuit. Besides, a dynamic regularization factor is added to iteration process to suppress noises and enhance accuracy. We verify the proposed method from the aspect of training samples, dimension, feature extraction and dimension reduction methods and noises in self-built database and Japan’s JAFFE and CMU’s CK database. Further, we compare this sparse method with classic SVM and RVM and analyze the recognition effect and time efficiency. The result of simulation experiment has shown that the coefficient of MSRR method contains classifying information, which is capable of improving the computing speed and achieving a satisfying recognition result.

Population coding in sparsely connected networks of noisy neurons.

Science.gov (United States)

Tripp, Bryan P; Orchard, Jeff

2012-01-01

This study examines the relationship between population coding and spatial connection statistics in networks of noisy neurons. Encoding of sensory information in the neocortex is thought to require coordinated neural populations, because individual cortical neurons respond to a wide range of stimuli, and exhibit highly variable spiking in response to repeated stimuli. Population coding is rooted in network structure, because cortical neurons receive information only from other neurons, and because the information they encode must be decoded by other neurons, if it is to affect behavior. However, population coding theory has often ignored network structure, or assumed discrete, fully connected populations (in contrast with the sparsely connected, continuous sheet of the cortex). In this study, we modeled a sheet of cortical neurons with sparse, primarily local connections, and found that a network with this structure could encode multiple internal state variables with high signal-to-noise ratio. However, we were unable to create high-fidelity networks by instantiating connections at random according to spatial connection probabilities. In our models, high-fidelity networks required additional structure, with higher cluster factors and correlations between the inputs to nearby neurons.

Robust Nonnegative Matrix Factorization via Joint Graph Laplacian and Discriminative Information for Identifying Differentially Expressed Genes

Directory of Open Access Journals (Sweden)

Ling-Yun Dai

2017-01-01

Full Text Available Differential expression plays an important role in cancer diagnosis and classification. In recent years, many methods have been used to identify differentially expressed genes. However, the recognition rate and reliability of gene selection still need to be improved. In this paper, a novel constrained method named robust nonnegative matrix factorization via joint graph Laplacian and discriminative information (GLD-RNMF is proposed for identifying differentially expressed genes, in which manifold learning and the discriminative label information are incorporated into the traditional nonnegative matrix factorization model to train the objective matrix. Specifically, L2,1-norm minimization is enforced on both the error function and the regularization term which is robust to outliers and noise in gene data. Furthermore, the multiplicative update rules and the details of convergence proof are shown for the new model. The experimental results on two publicly available cancer datasets demonstrate that GLD-RNMF is an effective method for identifying differentially expressed genes.

Confidence of model based shape reconstruction from sparse data

DEFF Research Database (Denmark)

Baka, N.; de Bruijne, Marleen; Reiber, J. H. C.

2010-01-01

Statistical shape models (SSM) are commonly applied for plausible interpolation of missing data in medical imaging. However, when fitting a shape model to sparse information, many solutions may fit the available data. In this paper we derive a constrained SSM to fit noisy sparse input landmarks...

Effects of matrix metallproteinases on dentin bonding and strategies to increase durability of dentin adhesion

Directory of Open Access Journals (Sweden)

Jung-Hyun Lee

2012-02-01

Full Text Available The limited durability of resin-dentin bonds severely compromises the longevity of composite resin restorations. Resin-dentin bond degradation might occur via degradation of water-rich and resin sparse collagen matrices by host-derived matrix metalloproteinases (MMPs. This review article provides overview of current knowledge of the role of MMPs in dentin matrix degradation and four experimental strategies for extending the longevity of resin-dentin bonds. They include: (1 the use of broad-spectrum inhibitors of MMPs, (2 the use of cross-linking agents for silencing the activities of MMPs, (3 ethanol wet-bonding with hydrophobic resin, (4 biomimetic remineralization of water-filled collagen matrix. A combination of these strategies will be able to overcome the limitations in resin-dentin adhesion.

Proportionate Minimum Error Entropy Algorithm for Sparse System Identification

Directory of Open Access Journals (Sweden)

Zongze Wu

2015-08-01

Full Text Available Sparse system identification has received a great deal of attention due to its broad applicability. The proportionate normalized least mean square (PNLMS algorithm, as a popular tool, achieves excellent performance for sparse system identification. In previous studies, most of the cost functions used in proportionate-type sparse adaptive algorithms are based on the mean square error (MSE criterion, which is optimal only when the measurement noise is Gaussian. However, this condition does not hold in most real-world environments. In this work, we use the minimum error entropy (MEE criterion, an alternative to the conventional MSE criterion, to develop the proportionate minimum error entropy (PMEE algorithm for sparse system identification, which may achieve much better performance than the MSE based methods especially in heavy-tailed non-Gaussian situations. Moreover, we analyze the convergence of the proposed algorithm and derive a sufficient condition that ensures the mean square convergence. Simulation results confirm the excellent performance of the new algorithm.

Sparse PDF Volumes for Consistent Multi-Resolution Volume Rendering

KAUST Repository

Sicat, Ronell Barrera

2014-12-31

This paper presents a new multi-resolution volume representation called sparse pdf volumes, which enables consistent multi-resolution volume rendering based on probability density functions (pdfs) of voxel neighborhoods. These pdfs are defined in the 4D domain jointly comprising the 3D volume and its 1D intensity range. Crucially, the computation of sparse pdf volumes exploits data coherence in 4D, resulting in a sparse representation with surprisingly low storage requirements. At run time, we dynamically apply transfer functions to the pdfs using simple and fast convolutions. Whereas standard low-pass filtering and down-sampling incur visible differences between resolution levels, the use of pdfs facilitates consistent results independent of the resolution level used. We describe the efficient out-of-core computation of large-scale sparse pdf volumes, using a novel iterative simplification procedure of a mixture of 4D Gaussians. Finally, our data structure is optimized to facilitate interactive multi-resolution volume rendering on GPUs.

SHMF: Interest Prediction Model with Social Hub Matrix Factorization

Directory of Open Access Journals (Sweden)

Chaoyuan Cui

2017-01-01

Full Text Available With the development of social networks, microblog has become the major social communication tool. There is a lot of valuable information such as personal preference, public opinion, and marketing in microblog. Consequently, research on user interest prediction in microblog has a positive practical significance. In fact, how to extract information associated with user interest orientation from the constantly updated blog posts is not so easy. Existing prediction approaches based on probabilistic factor analysis use blog posts published by user to predict user interest. However, these methods are not very effective for the users who post less but browse more. In this paper, we propose a new prediction model, which is called SHMF, using social hub matrix factorization. SHMF constructs the interest prediction model by combining the information of blogs posts published by both user and direct neighbors in user’s social hub. Our proposed model predicts user interest by integrating user’s historical behavior and temporal factor as well as user’s friendships, thus achieving accurate forecasts of user’s future interests. The experimental results on Sina Weibo show the efficiency and effectiveness of our proposed model.

Speckle suppression via sparse representation for wide-field imaging through turbid media.

Science.gov (United States)

Jang, Hwanchol; Yoon, Changhyeong; Chung, Euiheon; Choi, Wonshik; Lee, Heung-No

2014-06-30

Speckle suppression is one of the most important tasks in the image transmission through turbid media. Insufficient speckle suppression requires an additional procedure such as temporal ensemble averaging over multiple exposures. In this paper, we consider the image recovery process based on the so-called transmission matrix (TM) of turbid media for the image transmission through the media. We show that the speckle left unremoved in the TM-based image recovery can be suppressed effectively via sparse representation (SR). SR is a relatively new signal reconstruction framework which works well even for ill-conditioned problems. This is the first study to show the benefit of using the SR as compared to the phase conjugation (PC) a de facto standard method to date for TM-based imaging through turbid media including a live cell through tissue slice.

A flexible framework for sparse simultaneous component based data integration

Directory of Open Access Journals (Sweden)

Van Deun Katrijn

2011-11-01

Full Text Available Abstract 1 Background High throughput data are complex and methods that reveal structure underlying the data are most useful. Principal component analysis, frequently implemented as a singular value decomposition, is a popular technique in this respect. Nowadays often the challenge is to reveal structure in several sources of information (e.g., transcriptomics, proteomics that are available for the same biological entities under study. Simultaneous component methods are most promising in this respect. However, the interpretation of the principal and simultaneous components is often daunting because contributions of each of the biomolecules (transcripts, proteins have to be taken into account. 2 Results We propose a sparse simultaneous component method that makes many of the parameters redundant by shrinking them to zero. It includes principal component analysis, sparse principal component analysis, and ordinary simultaneous component analysis as special cases. Several penalties can be tuned that account in different ways for the block structure present in the integrated data. This yields known sparse approaches as the lasso, the ridge penalty, the elastic net, the group lasso, sparse group lasso, and elitist lasso. In addition, the algorithmic results can be easily transposed to the context of regression. Metabolomics data obtained with two measurement platforms for the same set of Escherichia coli samples are used to illustrate the proposed methodology and the properties of different penalties with respect to sparseness across and within data blocks. 3 Conclusion Sparse simultaneous component analysis is a useful method for data integration: First, simultaneous analyses of multiple blocks offer advantages over sequential and separate analyses and second, interpretation of the results is highly facilitated by their sparseness. The approach offered is flexible and allows to take the block structure in different ways into account. As such

A flexible framework for sparse simultaneous component based data integration.

Science.gov (United States)

Van Deun, Katrijn; Wilderjans, Tom F; van den Berg, Robert A; Antoniadis, Anestis; Van Mechelen, Iven

2011-11-15

High throughput data are complex and methods that reveal structure underlying the data are most useful. Principal component analysis, frequently implemented as a singular value decomposition, is a popular technique in this respect. Nowadays often the challenge is to reveal structure in several sources of information (e.g., transcriptomics, proteomics) that are available for the same biological entities under study. Simultaneous component methods are most promising in this respect. However, the interpretation of the principal and simultaneous components is often daunting because contributions of each of the biomolecules (transcripts, proteins) have to be taken into account. We propose a sparse simultaneous component method that makes many of the parameters redundant by shrinking them to zero. It includes principal component analysis, sparse principal component analysis, and ordinary simultaneous component analysis as special cases. Several penalties can be tuned that account in different ways for the block structure present in the integrated data. This yields known sparse approaches as the lasso, the ridge penalty, the elastic net, the group lasso, sparse group lasso, and elitist lasso. In addition, the algorithmic results can be easily transposed to the context of regression. Metabolomics data obtained with two measurement platforms for the same set of Escherichia coli samples are used to illustrate the proposed methodology and the properties of different penalties with respect to sparseness across and within data blocks. Sparse simultaneous component analysis is a useful method for data integration: First, simultaneous analyses of multiple blocks offer advantages over sequential and separate analyses and second, interpretation of the results is highly facilitated by their sparseness. The approach offered is flexible and allows to take the block structure in different ways into account. As such, structures can be found that are exclusively tied to one data platform

Using a grid platform for solving large sparse linear systems over GF(2)

OpenAIRE

Kleinjung , Thorsten; Nussbaum , Lucas; Thomé , Emmanuel

2010-01-01

International audience; In Fall 2009, the final step of the factorization of rsa768 was carried out on several clusters of the Grid'5000 platform, leading to a new record in integer factorization. This step involves solving a huge sparse linear system defined over the binary field GF(2). This article aims at describing the algorithm used, the difficulties encountered, and the methodology which led to success. In particular, we illustrate how our use of the block Wiedemann algorithm led to a m...

Improving the energy efficiency of sparse linear system solvers on multicore and manycore systems.

Science.gov (United States)

Anzt, H; Quintana-Ortí, E S

2014-06-28

While most recent breakthroughs in scientific research rely on complex simulations carried out in large-scale supercomputers, the power draft and energy spent for this purpose is increasingly becoming a limiting factor to this trend. In this paper, we provide an overview of the current status in energy-efficient scientific computing by reviewing different technologies used to monitor power draft as well as power- and energy-saving mechanisms available in commodity hardware. For the particular domain of sparse linear algebra, we analyse the energy efficiency of a broad collection of hardware architectures and investigate how algorithmic and implementation modifications can improve the energy performance of sparse linear system solvers, without negatively impacting their performance. © 2014 The Author(s) Published by the Royal Society. All rights reserved.

Iterative software kernels

Energy Technology Data Exchange (ETDEWEB)

Duff, I.

1994-12-31

This workshop focuses on kernels for iterative software packages. Specifically, the three speakers discuss various aspects of sparse BLAS kernels. Their topics are: `Current status of user lever sparse BLAS`; Current status of the sparse BLAS toolkit`; and `Adding matrix-matrix and matrix-matrix-matrix multiply to the sparse BLAS toolkit`.

Feature selection and multi-kernel learning for sparse representation on a manifold

KAUST Repository

Wang, Jim Jing-Yan

2014-03-01

Sparse representation has been widely studied as a part-based data representation method and applied in many scientific and engineering fields, such as bioinformatics and medical imaging. It seeks to represent a data sample as a sparse linear combination of some basic items in a dictionary. Gao etal. (2013) recently proposed Laplacian sparse coding by regularizing the sparse codes with an affinity graph. However, due to the noisy features and nonlinear distribution of the data samples, the affinity graph constructed directly from the original feature space is not necessarily a reliable reflection of the intrinsic manifold of the data samples. To overcome this problem, we integrate feature selection and multiple kernel learning into the sparse coding on the manifold. To this end, unified objectives are defined for feature selection, multiple kernel learning, sparse coding, and graph regularization. By optimizing the objective functions iteratively, we develop novel data representation algorithms with feature selection and multiple kernel learning respectively. Experimental results on two challenging tasks, N-linked glycosylation prediction and mammogram retrieval, demonstrate that the proposed algorithms outperform the traditional sparse coding methods. © 2013 Elsevier Ltd.

Feature selection and multi-kernel learning for sparse representation on a manifold.

Science.gov (United States)

Wang, Jim Jing-Yan; Bensmail, Halima; Gao, Xin

2014-03-01

Sparse representation has been widely studied as a part-based data representation method and applied in many scientific and engineering fields, such as bioinformatics and medical imaging. It seeks to represent a data sample as a sparse linear combination of some basic items in a dictionary. Gao et al. (2013) recently proposed Laplacian sparse coding by regularizing the sparse codes with an affinity graph. However, due to the noisy features and nonlinear distribution of the data samples, the affinity graph constructed directly from the original feature space is not necessarily a reliable reflection of the intrinsic manifold of the data samples. To overcome this problem, we integrate feature selection and multiple kernel learning into the sparse coding on the manifold. To this end, unified objectives are defined for feature selection, multiple kernel learning, sparse coding, and graph regularization. By optimizing the objective functions iteratively, we develop novel data representation algorithms with feature selection and multiple kernel learning respectively. Experimental results on two challenging tasks, N-linked glycosylation prediction and mammogram retrieval, demonstrate that the proposed algorithms outperform the traditional sparse coding methods. Copyright © 2013 Elsevier Ltd. All rights reserved.

Sparse representation, modeling and learning in visual recognition theory, algorithms and applications

CERN Document Server

Cheng, Hong

2015-01-01

This unique text/reference presents a comprehensive review of the state of the art in sparse representations, modeling and learning. The book examines both the theoretical foundations and details of algorithm implementation, highlighting the practical application of compressed sensing research in visual recognition and computer vision. Topics and features: provides a thorough introduction to the fundamentals of sparse representation, modeling and learning, and the application of these techniques in visual recognition; describes sparse recovery approaches, robust and efficient sparse represen

Comparison of Methods for Sparse Representation of Musical Signals

DEFF Research Database (Denmark)

Endelt, Line Ørtoft; la Cour-Harbo, Anders

2005-01-01

by a number of sparseness measures and results are shown on the ℓ1 norm of the coefficients, using a dictionary containing a Dirac basis, a Discrete Cosine Transform, and a Wavelet Packet. Evaluated only on the sparseness Matching Pursuit is the best method, and it is also relatively fast....

A New EM CKM Matrix: Implications of the Nucleon Strange Quark Content, Anomalous Magnetic Moments of Nucleons and Electric and Magnetic Nucleon Form Factors

Science.gov (United States)

Ward, Thomas

2013-10-01

A new electromagnetic neutral-current quark mixing matrix, analog to the well-known Cabibbo-Kobayashi-Maskawa (CKM) weak charge-current matrix, is proposed to account for the strange quark content of the neutron and proton and part of the anomalous axial vector magnetic moments. The EM-CKM matrix is shown to be equivalent to the weak-CKM matrix following an EM to weak gauge symmetry transformation, demonstrating the universality of the Standard Model (SM) CKM quark mixing matrix. The electric and magnetic form factors are reformulated using a new QCD three quark nucleon gyromagnetic factor, Dirac and Pauli form factors and anomalous kappa factors. The old 1943 Jauch form factors which have been systematically used and developed for many years is shown to be in stark disagreement with the new global set of experimental polarized electron-proton scattering data whereas the reformulated SM parameter set of this study is shown to agree very well, lending strong support for this new EM SM approach.

Nonleachable Imidazolium-Incorporated Composite for Disruption of Bacterial Clustering, Exopolysaccharide-Matrix Assembly, and Enhanced Biofilm Removal.

Science.gov (United States)

Hwang, Geelsu; Koltisko, Bernard; Jin, Xiaoming; Koo, Hyun

2017-11-08

Surface-grown bacteria and production of an extracellular polymeric matrix modulate the assembly of highly cohesive and firmly attached biofilms, making them difficult to remove from solid surfaces. Inhibition of cell growth and inactivation of matrix-producing bacteria can impair biofilm formation and facilitate removal. Here, we developed a novel nonleachable antibacterial composite with potent antibiofilm activity by directly incorporating polymerizable imidazolium-containing resin (antibacterial resin with carbonate linkage; ABR-C) into a methacrylate-based scaffold (ABR-modified composite; ABR-MC) using an efficient yet simplified chemistry. Low-dose inclusion of imidazolium moiety (∼2 wt %) resulted in bioactivity with minimal cytotoxicity without compromising mechanical integrity of the restorative material. The antibiofilm properties of ABR-MC were assessed using an exopolysaccharide-matrix-producing (EPS-matrix-producing) oral pathogen (Streptococcus mutans) in an experimental biofilm model. Using high-resolution confocal fluorescence imaging and biophysical methods, we observed remarkable disruption of bacterial accumulation and defective 3D matrix structure on the surface of ABR-MC. Specifically, the antibacterial composite impaired the ability of S. mutans to form organized bacterial clusters on the surface, resulting in altered biofilm architecture with sparse cell accumulation and reduced amounts of EPS matrix (versus control composite). Biofilm topology analyses on the control composite revealed a highly organized and weblike EPS structure that tethers the bacterial clusters to each other and to the surface, forming a highly cohesive unit. In contrast, such a structured matrix was absent on the surface of ABR-MC with mostly sparse and amorphous EPS, indicating disruption in the biofilm physical stability. Consistent with lack of structural organization, the defective biofilm on the surface of ABR-MC was readily detached when subjected to low shear