Smoothed Low Rank and Sparse Matrix Recovery by Iteratively Reweighted Least Squares Minimization

This paper presents a general framework for solving the low-rank and/or sparse matrix minimization problems, which may involve multiple nonsmooth terms. The iteratively reweighted least squares (IRLSs) method is a fast solver, which smooths the objective function and minimizes it by alternately updating the variables and their weights. However, the traditional IRLS can only solve a sparse only or low rank only minimization problem with squared loss or an affine constraint. This paper generalizes IRLS to solve joint/mixed low-rank and sparse minimization problems, which are essential formulations for many tasks. As a concrete example, we solve the Schatten-p norm and ℓ2,q-norm regularized low-rank representation problem by IRLS, and theoretically prove that the derived solution is a stationary point (globally optimal if p, q ≥ 1). Our convergence proof of IRLS is more general than previous one that depends on the special properties of the Schatten-p norm and ℓ2,q-norm. Extensive experiments on both synthetic and real data sets demonstrate that our IRLS is much more efficient.

• Publication year

  2014

• Venue

  IEEE Transactions on Image Processing

• Publication date

  2014-01-28

• Fields of study

  Mathematics, Computer Science, Medicine

• Identifiers
  DOI 10.1109/TIP.2014.2380155arXiv 1401.7413PMID 25531948
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Generalized Nonconvex Nonsmooth Low-Rank Minimization

  2014cited by this paper
• Proximal Iteratively Reweighted Algorithm with Multiple Splitting for Nonconvex Sparsity Optimization

  2014cited by this paper
• Generalized Singular Value Thresholding

  2014cited by this paper
• Correlation Adaptive Subspace Segmentation by Trace Lasso

  2013cited by this paper
• Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization

  2012influential reference
• Compressed Sensing

  2012cited by this paper
• Robust and Efficient Subspace Segmentation via Least Squares Regression

  2012cited by this paper
• Iterative reweighted algorithms for matrix rank minimization

  2012cited by this paper
• Reweighted 1-Minimization for Sparse Solutions to Underdetermined Linear Systems

  2012cited by this paper
• Inductive Robust Principal Component Analysis

  2012influential reference
• Non-negative low rank and sparse graph for semi-supervised learning

  2012influential reference
• Robust Matrix Decomposition With Sparse Corruptions

  2011cited by this paper
• Latent Low-Rank Representation for subspace segmentation and feature extraction

  2011cited by this paper
• Linearized Alternating Direction Method with Gaussian Back Substitution for Separable Convex Programming

  2011cited by this paper
• Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation

  2011influential reference
• The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices

  2010cited by this paper
• Robust Subspace Segmentation by Low-Rank Representation

  2010influential reference
• A Simple Algorithm for Nuclear Norm Regularized Problems

  2010influential reference
• Matrix Completion With Noise

  2009cited by this paper
• On the ADI method for Sylvester equations

  2009cited by this paper
• Robust principal component analysis?

  2009cited by this paper
• Robust Face Recognition via Sparse Representation

  2009cited by this paper
• Tree-Guided Group Lasso for Multi-Task Regression with Structured Sparsity

  2009influential reference
• An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems

  2009cited by this paper
• Sparsest solutions of underdetermined linear systems via ℓq-minimization for 0

  2009cited by this paper
• Group lasso with overlap and graph lasso

  2009influential reference
• Iteratively reweighted least squares minimization for sparse recovery

  2008cited by this paper
• Iteratively reweighted algorithms for compressive sensing

  2008cited by this paper
• Exact Matrix Completion via Convex Optimization

  2008cited by this paper
• Functions of matrices - theory and computation

  2008cited by this paper
• COFI RANK - Maximum Margin Matrix Factorization for Collaborative Ranking

  2007cited by this paper
• Enhancing Sparsity by Reweighted ℓ1 Minimization

  2007cited by this paper
• Model selection and estimation in regression with grouped variables

  2006cited by this paper
• Eigenvalue Inequalities for Matrix Product

  2006cited by this paper
• The CMU Pose, Illumination, and Expression Database

  2003cited by this paper
• From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

  2001cited by this paper
• Lanczos Bidiagonalization With Partial Reorthogonalization

  1998influential reference
• Normalized cuts and image segmentation

  1997cited by this paper
• Regression Shrinkage and Selection via the Lasso

  1996cited by this paper
• C Xxxx Society for Industrial and Applied Mathematics Improved Iteratively Reweighted Least Squares for Unconstrained Smoothed Q Minimization *

  year unknowncited by this paper

• DOA Estimation in Distributed Nested Arrays Using Multifrequency Information Extrapolation

  2026cites this paper
• Multi-attribute graph learning for geoscience applications

  2026cites this paper
• Joint DOA Estimation and Distorted Sensor Detection

  2025cites this paper
• Block-diagonal graph embedding for unsupervised feature selection

  2025cites this paper
• Robust Low-Rank Reconstruction of Seismic Data

  2025cites this paper
• Adaptive kernel subspace clustering with discrete group structure constraint

  2025cites this paper
• Efficient Image Classification via Structured Low-Rank Matrix Factorization Regression

  2024cites this paper
• Robust Self-expression Learning with Adaptive Noise Perception

  2024cites this paper
• Robust DOA Estimation With Distorted Sensors

  2024cites this paper
• Reweighted Quasi Norm Regularized Low-Rank Factorization for Matrix Robust PCA

  2024cites this paper
• Enhancing generalized spectral clustering with embedding Laplacian graph regularization

  2024cites this paper
• Faster nonconvex low-rank matrix learning for image low-level and high-level vision: A unified framework

  2024cites this paper
• Accelerated PALM for Nonconvex Low-Rank Matrix Recovery With Theoretical Analysis

  2024cites this paper
• Linear Regression Problem Relaxations Solved by Nonconvex ADMM With Convergence Analysis

  2024cites this paper
• Online Measurement Scheme and Solution for Frequency Response Characteristics of CVT

  2023cites this paper
• Low-rank matrix recovery via novel double nonconvex nonsmooth rank minimization with ADMM

  2023cites this paper
• Joint angular-frequency distribution estimation via spatial-temporal sparse sampling and low-rank matrix recovery

  2023cites this paper
• Joint modeling of playing time and purchase propensity in massively multiplayer online role-playing games using crossed random effects

  2023cites this paper
• Iteratively Re-Weighted Method for Sparsity-Inducing Norms

  2023cites this paper
• Efficient and Effective Nonconvex Low-Rank Subspace Clustering via SVT-Free Operators

  2023influential citation
• Image classification based on weighted nonconvex low-rank and discriminant least squares regression

  2023cites this paper
• Joint DOA Estimation and Distorted Sensor Detection Under Entangled Low-Rank and Row-Sparse Constraints

  2023cites this paper
• Data-Driven Spectrum Partition for Multiplexing URLLC and eMBB

  2023cites this paper
• Unified Framework for Faster Clustering via Joint Schatten p-Norm Factorization With Optimal Mean

  2023cites this paper
• Image Segmentation Based on Fuzzy Low-Rank Structural Clustering

  2023cites this paper
• Convergence analysis of consensus-ADMM for general QCQP

  2022cites this paper
• Proximal linearization methods for Schatten p-quasi-norm minimization

  2022cites this paper
• Accelerated Detection for Low-Field NMR Using Nonuniform Sampling and Improved Reconstruction

  2022cites this paper
• Multi-view dimensionality reduction learning with hierarchical sparse feature selection

  2022cites this paper
• Generalized Nonconvex Nonsmooth Low-Rank Matrix Recovery Framework With Feasible Algorithm Designs and Convergence Analysis

  2022influential citation
• Research on infrared dim and small target detection algorithm based on frequency domain difference

  2022cites this paper
• Optimistic optimisation of composite objective with exponentiated update

  2022cites this paper
• Low-Rank and Row-Sparse Decomposition for Joint DOA Estimation and Distorted Sensor Detection

  2022cites this paper
• Fast Extended Inductive Robust Principal Component Analysis With Optimal Mean

  2022cites this paper
• Cross-Domain Object Representation via Robust Low-Rank Correlation Analysis

  2021cites this paper
• Stable and Compact Face Recognition via Unlabeled Data Driven Sparse Representation-Based Classification

  2021cites this paper
• Virtual samples based robust block-diagonal dictionary learning for face recognition

  2021cites this paper
• Rank revealing-based tensor completion using improved generalized tensor multi-rank minimization

  2021cites this paper
• Robust Recovery of Low Rank Matrix by Nonconvex Rank Regularization

  2021cites this paper
• Structure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attacks

  2021cites this paper
• A Novel Decomposition Model for Visual Rail Surface Inspection

  2021cites this paper
• Structure-Oriented Progressive Low-Rank Image Restoration for Defending Adversarial Attacks

  2021cites this paper
• Semi-Supervised Low-Rank Semantics Grouping for Zero-Shot Learning

  2021cites this paper
• Matrix completion with column outliers and sparse noise

  2021cites this paper
• Low-Rank and Sparse Decomposition for Joint DOA Estimation and Contaminated Sensors Detection with Sparsely Contaminated Arrays

  2021cites this paper
• Hyperspectral Image Classification via Multi-Feature-Based Correlation Adaptive Representation

  2021cites this paper
• Drug-Target Interaction Identification via Dual-Graph Regularized Robust PCA in Heterogeneous Networks

  2021cites this paper
• Robust Matrix Completion With Column Outliers

  2021cites this paper
• Total Variation Regularization Based on Iteratively Reweighted Least-Squares Method for Electrical Resistance Tomography

  2020cites this paper
• An Analysis of Sketched IRLS for Accelerated Sparse Residual Regression

  2020cites this paper
• Analog-to-Information Conversion for Nonstationary Signals

  2020cites this paper
• A new two-stage method for single image rain removal

  2020cites this paper
• Low-Rank Approximation via Generalized Reweighted Iterative Nuclear and Frobenius Norms

  2020cites this paper
• A Group Norm Regularized LRR Factorization Model for Spectral Clustering

  2020influential citation
• A Group Norm Regularized Factorization Model for Subspace Segmentation

  2020cites this paper
• Low-Rank Matrix Recovery for Topological Interference Management

  2020cites this paper
• A New Estimation Algorithm for Frequency and Amplitude in Harmonic Signal Processing

  2020cites this paper
• DOA Estimation in Impulsive Noise via Low-Rank Matrix Approximation and Weakly Convex Optimization

  2019cites this paper
• LRR for Subspace Segmentation via Tractable Schatten- $p$ Norm Minimization and Factorization

  2019influential citation
• Matrix Completion Based on Non-Convex Low-Rank Approximation

  2019cites this paper
• Sparsity-regularized feature selection for multi-class remote sensing image classification

  2019cites this paper
• Structurally Incoherent Low-Rank 2DLPP for Image Classification

  2019cites this paper
• Block-sparse signal recovery based on truncated ℓ 1 minimisation in non-Gaussian noise

  2019cites this paper
• Weighted Mixed-Norm Regularized Regression for Robust Face Identification

  2019cites this paper
• Nonparametric Blind Super-Resolution Using Adaptive Heavy-Tailed Priors

  2019cites this paper
• Sparse subspace clustering via smoothed ℓp minimization

  2019cites this paper
• A Large-Scale Constrained Joint Modeling Approach for Predicting User Activity, Engagement, and Churn With Application to Freemium Mobile Games

  2019cites this paper
• Single-image de-raining using low-rank matrix approximation

  2019cites this paper
• Ensemble clustering based on dense representation

  2019cites this paper
• Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms

  2019cites this paper
• Robust Image Recovery via Affine Transformation and $L_{2,1}$ Norm

  2019cites this paper
• An Optimization Algorithm of Robust Principal Component Analysis and Its Application

  2019cites this paper
• Nonconvex Regularized Robust PCA Using the Proximal Block Coordinate Descent Algorithm

  2019cites this paper
• Krylov Methods for Low-Rank Regularization

  2019cites this paper
• Nonconvex Robust Low-Rank Tensor Reconstruction via an Empirical Bayes Method

  2019cites this paper
• Low-Rank Approximation via the Generalized Reweighted Iterative Nuclear Norm

  2019cites this paper
• Nonconvex Low Tubal Rank Tensor Minimization

  2019cites this paper
• Low-Rank Matrix Recovery via Modified Schatten- $p$ Norm Minimization With Convergence Guarantees

  2019influential citation
• Feature selection via kernel sparse representation

  2019cites this paper
• Variety-Based Background Subtraction for Nonlinear Trajectory Tracking

  2019cites this paper
• Sparse subspace clustering via smoothed (cid:96) p minimization

  2019cites this paper
• MF-LRTC: Multi-filters guided low-rank tensor coding for image restoration

  2018cites this paper
• Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications

  2018influential citation
• An algorithm for low-rank matrix factorization and its applications

  2018cites this paper
• Robust discriminant low-rank representation for subspace clustering

  2018cites this paper
• Background recovery via motion-based robust principal component analysis with matrix factorization

  2018cites this paper
• Majorization-Minimization-Based Sparse Signal Recovery Method Using Prior Support and Amplitude Information for the Estimation of Time-varying Sparse Channels

  2018cites this paper
• Nonlinear sparse feature selection algorithm via low matrix rank constraint

  2018cites this paper
• Low Rank Regularization: A review

  2018cites this paper
• Low-rank dimensionality reduction for multi-modality neurodegenerative disease identification

  2018cites this paper
• Using Joint Generalized Eigenvectors of a Set of Covariance Matrix Pencils for Deflationary Blind Source Extraction

  2018cites this paper
• Implicit Block Diagonal Low-Rank Representation

  2018influential citation
• Unsupervised nonlinear feature selection algorithm via kernel function

  2018cites this paper
• Sparse and low-rank recovery using adaptive thresholding

  2018cites this paper
• Reweighted Low-Rank Matrix Analysis With Structural Smoothness for Image Denoising

  2018cites this paper
• Stochastic Chebyshev Gradient Descent for Spectral Optimization

  2018cites this paper
• A Comprehensive Survey for Low Rank Regularization

  2018cites this paper
• Proximal iteratively reweighted algorithm for low-rank matrix recovery

  2018cites this paper
• Optimizing Spectral Sums using Randomized Chebyshev Expansions

  2018cites this paper
• Reconstruction of Structurally-Incomplete Matrices With Reweighted Low-Rank and Sparsity Priors

  2017cites this paper