Convergence of a block coordinate descent method for nondifferentiable minimization

DOI10.1023/A:1017501703105zbMath1006.65062OpenAlexW1540764732MaRDI QIDQ5945065

Paul Tseng

Publication date: 16 February 2003

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1017501703105

zbMATH Keywords

convergencequasiconvex functionsGauss-Seidel methodstationary pointblock coordinate descent methodnondifferentiable minimizationproximal minimization algorithmpseudoconvex functions

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30)

Related Items

Greedy algorithms for prediction, An attention algorithm for solving large scale structured \(l_0\)-norm penalty estimation problems, GMM based simultaneous reconstruction and segmentation in X-ray CT application, Sparse group Lasso and high dimensional multinomial classification, Solving norm constrained portfolio optimization via coordinate-wise descent algorithms, On the rate of convergence of the proximal alternating linearized minimization algorithm for convex problems, Penalized logspline density estimation using total variation penalty, Conditional score matching for high-dimensional partial graphical models, An alternating direction method of multipliers for MCP-penalized regression with high-dimensional data, Inexact coordinate descent: complexity and preconditioning, Influence of forecasting electricity prices in the optimization of complex hydrothermal systems, The shooting S-estimator for robust regression, A fast patch-dictionary method for whole image recovery, Quadratic scalarization for decomposed multiobjective optimization, Block coordinate proximal gradient methods with variable Bregman functions for nonsmooth separable optimization, Identification of proportionality structure with two-part models using penalization, Natural coordinate descent algorithm for \(\ell_1\)-penalised regression in generalised linear models, Distance metric learning guided adaptive subspace semi-supervised clustering, A lasso for hierarchical interactions, Geometry preserving multi-task metric learning, Approximation accuracy, gradient methods, and error bound for structured convex optimization, A globally convergent algorithm for nonconvex optimization based on block coordinate update, A storm of feasibility pumps for nonconvex MINLP, Cost-to-travel functions: a new perspective on optimal and model predictive control, A primal dual active set with continuation algorithm for the \(\ell^0\)-regularized optimization problem, \(\ell_{1}\)-penalization for mixture regression models, Proximal alternating linearized minimization for nonconvex and nonsmooth problems, Coordinate descent algorithm for covariance graphical Lasso, Sparse identification of posynomial models, Algorithm for overcoming the curse of dimensionality for time-dependent non-convex Hamilton-Jacobi equations arising from optimal control and differential games problems, Split Bregman method for large scale fused Lasso, X-ray CT image reconstruction via wavelet frame based regularization and Radon domain inpainting, Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm, Hierarchical sparse modeling: a choice of two group Lasso formulations, The solution path of the generalized lasso, Inferring sparse Gaussian graphical models with latent structure, Penalized model-based clustering with unconstrained covariance matrices, Proximal point method for minimizing quasiconvex locally Lipschitz functions on Hadamard manifolds, A new nonconvex approach to low-rank matrix completion with application to image inpainting, A block coordinate gradient descent method for regularized convex separable optimization and covariance selection, Sparse non-negative tensor factorization using columnwise coordinate descent, Extended ADMM and BCD for nonseparable convex minimization models with quadratic coupling terms: convergence analysis and insights, Graph optimization for dimensionality reduction with sparsity constraints, Stochastic block-coordinate gradient projection algorithms for submodular maximization, Large-scale unit commitment under uncertainty: an updated literature survey, Cyclic coordinate descent in hydrothermal nonsmooth problems, Asynchronous parallel primal-dual block coordinate update methods for affinely constrained convex programs, On the linear convergence of the approximate proximal splitting method for non-smooth convex optimization, Cyclic coordinate descent in a class of bang-singular-bang problems, Control of MIMO nonlinear systems: a data-driven model inversion approach, On the complexity analysis of randomized block-coordinate descent methods, A new alternating direction method for linearly constrained nonconvex optimization problems, An inexact PAM method for computing Wasserstein barycenter with unknown supports, Pairwise fusion approach incorporating prior constraint information, A mixture of nuclear norm and matrix factorization for tensor completion, GAITA: a Gauss-Seidel iterative thresholding algorithm for \(\ell_q\) regularized least squares regression, Alternating direction method of multipliers for a class of nonconvex bilinear optimization: convergence analysis and applications, Advanced algorithms for penalized quantile and composite quantile regression, Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection, A coordinate gradient descent method for nonsmooth separable minimization, Iteration complexity analysis of block coordinate descent methods, A higher-order LQ decomposition for separable covariance models, SOR- and Jacobi-type iterative methods for solving \(\ell_1 - \ell_2\) problems by way of Fenchel duality, Schwarz iterative methods: infinite space splittings, Equity portfolio management with cardinality constraints and risk parity control using multi-objective particle swarm optimization, Surveying and comparing simultaneous sparse approximation (or group-lasso) algorithms, Cyclic seesaw process for optimization and identification, Missing values: sparse inverse covariance estimation and an extension to sparse regression, Estimating time-varying networks, SZ and CMB reconstruction using generalized morphological component analysis, Processing MUSE hyperspectral data: denoising, deconvolution and detection of astrophysical sources, Sparse Principal Component Analysis via Variable Projection, Lower bounds for cubic optimization over the sphere, A block coordinate variable metric forward-backward algorithm, Graph sparse nonnegative matrix factorization algorithm based on the inertial projection neural network, Estimation of high-dimensional graphical models using regularized score matching, A class of problems for which cyclic relaxation converges linearly, Robust network-based analysis of the associations between (epi)genetic measurements, A unified primal dual active set algorithm for nonconvex sparse recovery, An application of the algorithm of the cyclic coordinate descent in multidimensional optimization problems with constrained speed, New cyclic sparsity measures for deconvolution based on convex relaxation, Two algorithms for fitting constrained marginal models, Multi-block Bregman proximal alternating linearized minimization and its application to orthogonal nonnegative matrix factorization, An effective procedure for feature subset selection in logistic regression based on information criteria, Joint variable and rank selection for parsimonious estimation of high-dimensional matrices, Partially distributed outer approximation, A block inertial Bregman proximal algorithm for nonsmooth nonconvex problems with application to symmetric nonnegative matrix tri-factorization, Majorization minimization by coordinate descent for concave penalized generalized linear models, Sparse group fused Lasso for model segmentation: a hybrid approach, Block-coordinate gradient descent method for linearly constrained nonsmooth separable optimization, Optimal representative sample weighting, An efficient alternating minimization method for fourth degree polynomial optimization, Linear support vector regression with linear constraints, Smoothing Newton method for \(\ell^0\)-\(\ell^2\) regularized linear inverse problem, Two-level monotonic multistage recommender systems, A maximum-margin multisphere approach for binary multiple instance learning, Biclustering analysis of functionals via penalized fusion, Feature selection for data integration with mixed multiview data, Parallel matrix factorization for low-rank tensor completion, A second-order method for strongly convex \(\ell _1\)-regularization problems, Parallel block coordinate minimization with application to group regularized regression, Structured regularization for conditional Gaussian graphical models, Variable selection for semiparametric regression models with iterated penalisation, Adaptive log-density estimation, High-Dimensional Heteroscedastic Regression with an Application to eQTL Data Analysis, On obtaining sparse semantic solutions for inverse problems, control, and neural network training, Block-coordinate and incremental aggregated proximal gradient methods for nonsmooth nonconvex problems, Distributed identification of heterogeneous treatment effects, A new double-regularized regression using Liu and Lasso regularization, An efficient parallel block coordinate descent algorithm for large-scale precision matrix estimation using graphics processing units, Performance of first- and second-order methods for \(\ell_1\)-regularized least squares problems, An Accelerated Randomized Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization, Block decomposition methods for total variation by primal-dual stitching, Efficient Blind Compressed Sensing Using Sparsifying Transforms with Convergence Guarantees and Application to Magnetic Resonance Imaging, Full convergence of the proximal point method for quasiconvex functions on Hadamard manifolds, Multivariate sparse group lasso for the multivariate multiple linear regression with an arbitrary group structure, Model Selection for Cox Models with Time-Varying Coefficients, The influence function of penalized regression estimators, Distributed Block Coordinate Descent for Minimizing Partially Separable Functions, Group variable selection via convex log‐exp‐sum penalty with application to a breast cancer survivor study, Convergence of incentive-driven dynamics in Fisher markets, Efficient block-coordinate descent algorithms for the group Lasso, Sparse latent factor regression models for genome-wide and epigenome-wide association studies, Inertial alternating direction method of multipliers for non-convex non-smooth optimization, Estimation of multivariate dependence structures via constrained maximum likelihood, Classes of linear programs solvable by coordinate-wise minimization, Integrative analysis of prognosis data on multiple cancer subtypes, An inexact continuation accelerated proximal gradient algorithm for lown-rank tensor recovery, An expectation-maximization algorithm for blind separation of noisy mixtures using Gaussian mixture model, Stable and robust LQR design via scenario approach, Scheduling for a processor sharing system with linear slowdown, Penalty decomposition methods for rank minimization, Separable approximations and decomposition methods for the augmented Lagrangian, Block Stochastic Gradient Iteration for Convex and Nonconvex Optimization, A block symmetric Gauss-Seidel decomposition theorem for convex composite quadratic programming and its applications, A parallelizable augmented Lagrangian method applied to large-scale non-convex-constrained optimization problems, Subgroup analysis of zero-inflated Poisson regression model with applications to insurance data, Sparse probabilistic K-means, Model-based regression clustering for high-dimensional data: application to functional data, Adaptive bi-level variable selection for multivariate failure time model with a diverging number of covariates, The blockwise coordinate descent method for integer programs, Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties, On the convergence of asynchronous parallel iteration with unbounded delays, Large-Scale Loan Portfolio Selection, Convergence of slice-based block coordinate descent algorithm for convolutional sparse coding, A Randomized Nonmonotone Block Proximal Gradient Method for a Class of Structured Nonlinear Programming, Synchronous parallel block coordinate descent method for nonsmooth convex function minimization, An efficient method for clustered multi-metric learning, Tensor factorization with total variation and Tikhonov regularization for low-rank tensor completion in imaging data, On global convergence of alternating least squares for tensor approximation, Hybrid Jacobian and Gauss--Seidel Proximal Block Coordinate Update Methods for Linearly Constrained Convex Programming, Autoregressive identification of Kronecker graphical models, The conditional censored graphical Lasso estimator, Worst-case complexity of cyclic coordinate descent: \(O(n^2)\) gap with randomized version, Distributed Deterministic Asynchronous Algorithms in Time-Varying Graphs Through Dykstra Splitting, Graphical model selection and estimation for high dimensional tensor data, Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function, A syncro-parallel nonsmooth PGD algorithm for nonsmooth optimization, Model-based feature selection and clustering of RNA-seq data for unsupervised subtype discovery, Pathwise coordinate optimization, Sparse regression for large data sets with outliers, Asynchronous Lagrangian scenario decomposition, On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization, A hierarchical multiple kernel support vector machine for customer churn prediction using longitudinal behavioral data, Morphological Diversity and Sparsity in Blind Source Separation, A Fast Active Set Block Coordinate Descent Algorithm for $\ell_1$-Regularized Least Squares, Additive models with trend filtering, Block Coordinate Descent Methods for Semidefinite Programming, Efficient computation for differential network analysis with applications to quadratic discriminant analysis, Robust Schatten-\(p\) norm based approach for tensor completion, An Efficient Inexact ABCD Method for Least Squares Semidefinite Programming, ROS regression: integrating regularization with optimal scaling regression, Lasso meets horseshoe: a survey, Regularized estimation of precision matrix for high-dimensional multivariate longitudinal data, Density Estimation by Total Variation Penalized Likelihood Driven by the Sparsity ℓ1 Information Criterion, Robust Coordinate Descent Algorithm Robust Solution Path for High-dimensional Sparse Regression Modeling, Computational Methods for Solving Nonconvex Block-Separable Constrained Quadratic Problems, Logical and test consistency in pairwise multiple comparisons, An Alternating Semiproximal Method for Nonconvex Regularized Structured Total Least Squares Problems, A Block Successive Upper-Bound Minimization Method of Multipliers for Linearly Constrained Convex Optimization, A variational proximal alternating linearized minimization in a given metric for limited-angle CT image reconstruction, Iterative Proportional Scaling Revisited: A Modern Optimization Perspective, A single image dehazing model using total variation and inter-channel correlation, Coordinate descent with arbitrary sampling II: expected separable overapproximation, On the convergence of the forward–backward splitting method with linesearches, Multivariate Gaussian network structure learning, Optimal multivariate Gaussian fitting with applications to PSF modeling in two-photon microscopy imaging, Unnamed Item, Risk-averse policy optimization via risk-neutral policy optimization, High-dimensional linear regression with hard thresholding regularization: theory and algorithm, Sparse regression at scale: branch-and-bound rooted in first-order optimization, Optimal replenishment order placement in a finite time horizon, Lasso penalized semiparametric regression on high-dimensional recurrent event data via coordinate descent, Convergence analysis for iterative data-driven tight frame construction scheme, A decomposition method for Lasso problems with zero-sum constraint, Two-way regularization for MEG source reconstruction via multilevel coordinate descent, Coordinate descent algorithms, Large-scale unit commitment under uncertainty, Penalized polygram regression, Four algorithms to solve symmetric multi-type non-negative matrix tri-factorization problem, Achieving the oracle property of OEM with nonconvex penalties, Model selection with distributed SCAD penalty, Block delayed Majorize-Minimize subspace algorithm for large scale image restoration ^*, Asynchronous variance-reduced block schemes for composite non-convex stochastic optimization: block-specific steplengths and adapted batch-sizes, Dual-Primal Domain Decomposition Methods for the Total Variation Minimization, On the uniqueness of solutions for the basis pursuit in the continuum, Robust low-rank tensor factorization by cyclic weighted median, Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity, A Scalable Hierarchical Lasso for Gene–Environment Interactions, Unnamed Item, Unnamed Item, A modified multinomial baseline logit model with logit functions having different covariates, A First-Order Optimization Algorithm for Statistical Learning with Hierarchical Sparsity Structure, Exact Penalization of Generalized Nash Equilibrium Problems, Cyclic Coordinate-Update Algorithms for Fixed-Point Problems: Analysis and Applications, On computation of semiparametric maximum likelihood estimators with shape constraints, An estimation approach for the influential-imitator diffusion, Activity propagation in systems of linear inequalities and its relation to block-coordinate descent in linear programs, Variable selection using penalised likelihoods for point patterns on a linear network, A multi-birth metric learning framework based on binary constraints, Joint association and classification analysis of multi‐view data, A proximal alternating minimization algorithm for the largest C-eigenvalue of piezoelectric-type tensors, Kronecker Product Approximation of Operators in Spectral Norm via Alternating SDP, Combining penalty‐based and Gauss–Seidel methods for solving stochastic mixed‐integer problems, Estimation of banded time-varying precision matrix based on SCAD and group Lasso, Covariance structure estimation with Laplace approximation, Compositional Graphical Lasso Resolves the Impact of Parasitic Infection on Gut Microbial Interaction Networks in a Zebrafish Model, Auto-weighted robust low-rank tensor completion via tensor-train, Iterative rank-one matrix completion via singular value decomposition and nuclear norm regularization, Block Policy Mirror Descent, Risk-averse optimization of reward-based coherent risk measures, A generalized conditional gradient method for dynamic inverse problems with optimal transport regularization, Multivariate expectile-based distribution: properties, Bayesian inference, and applications, A primal dual active set with continuation algorithm for high-dimensional nonconvex SICA-penalized regression, A modified information criterion for tuning parameter selection in 1d fused LASSO for inference on multiple change points, On the Efficiency of Random Permutation for ADMM and Coordinate Descent, Novel Proximal Gradient Methods for Nonnegative Matrix Factorization with Sparsity Constraints, Unnamed Item, Fast Nonoverlapping Block Jacobi Method for the Dual Rudin--Osher--Fatemi Model, Additive Schwarz Methods for Convex Optimization as Gradient Methods, Solving Partial Differential Equations on Manifolds From Incomplete Interpoint Distance, Sparse quadratic classification rules via linear dimension reduction, Grouped penalization estimation of the osteoporosis data in the traditional Chinese medicine, Independently Interpretable Lasso for Generalized Linear Models, Alternating Proximal Regularized Dictionary Learning, High-dimensional index tracking based on the adaptive elastic net, Asynchronous Schemes for Stochastic and Misspecified Potential Games and Nonconvex Optimization, Mixed-Effect Time-Varying Network Model and Application in Brain Connectivity Analysis, On the complexity of parallel coordinate descent, Unnamed Item, Unnamed Item, A Coordinate-Descent Primal-Dual Algorithm with Large Step Size and Possibly Nonseparable Functions, $\ell _0$ Minimization for wavelet frame based image restoration, Two Symmetrized Coordinate Descent Methods Can Be $O(n^2)$ Times Slower Than the Randomized Version, Integrative Analysis of Cancer Diagnosis Studies with Composite Penalization, Learning Sparse Causal Gaussian Networks With Experimental Intervention: Regularization and Coordinate Descent, Primal Domain Decomposition Methods for the Total Variation Minimization, Based on Dual Decomposition, An introduction to continuous optimization for imaging, A gradient method for the monotone fused least absolute shrinkage and selection operator, Joint Multichannel Deconvolution and Blind Source Separation, Blind Source Separation with Outliers in Transformed Domains, Group descent algorithms for nonconvex penalized linear and logistic regression models with grouped predictors, A fast unified algorithm for solving group-lasso penalize learning problems, An iterative algorithm for third-order tensor multi-rank minimization, A selective review of group selection in high-dimensional models, An ADMM with continuation algorithm for non-convex SICA-penalized regression in high dimensions, The sliding Frank–Wolfe algorithm and its application to super-resolution microscopy, Nested coordinate descent algorithms for empirical likelihood, Greedy approximate projection for magnetic resonance fingerprinting with partial volumes, Bi-level variable selection via adaptive sparse group Lasso, Sparse optimization for nonconvex group penalized estimation, Structural Pursuit Over Multiple Undirected Graphs, Functional Graphical Models, CoordinateWise Descent Methods for Leading Eigenvalue Problem, Alternating Structure-Adapted Proximal Gradient Descent for Nonconvex Nonsmooth Block-Regularized Problems, Estimation of Individualized Decision Rules Based on an Optimized Covariate-Dependent Equivalent of Random Outcomes, Relaxation algorithms for matrix completion, with applications to seismic travel-time data interpolation, An alternating minimization method for robust principal component analysis, Fast Best Subset Selection: Coordinate Descent and Local Combinatorial Optimization Algorithms, Computing the Best Approximation over the Intersection of a Polyhedral Set and the Doubly Nonnegative Cone, Incremental CP Tensor Decomposition by Alternating Minimization Method, Unnamed Item, Adaptive elastic-net selection in a quantile model with diverging number of variable groups, Iteration Complexity of a Block Coordinate Gradient Descent Method for Convex Optimization, Unnamed Item, Unnamed Item, Learning optical flow for fast MRI reconstruction, Toward Optimal Fingerprinting in Detection and Attribution of Changes in Climate Extremes, A Convergent 3-Block SemiProximal Alternating Direction Method of Multipliers for Conic Programming with 4-Type Constraints, Unnamed Item, Efficient computation of mean reverting portfolios using cyclical coordinate descent, A fast method for simultaneous reconstruction and segmentation in X-ray CT application, A non-convex regularization approach for stable estimation of loss development factors, An elastic-net penalized expectile regression with applications, Time-Varying Autoregression with Low-Rank Tensors, A novel regularization method for estimation and variable selection in multi-index models, Bregman Finito/MISO for Nonconvex Regularized Finite Sum Minimization without Lipschitz Gradient Continuity, Proximal Gradient Methods with Adaptive Subspace Sampling, Control analysis and design via randomised coordinate polynomial minimisation, Estimation of Gaussian directed acyclic graphs using partial ordering information with applications to DREAM3 networks and dairy cattle data, An efficient GPU-parallel coordinate descent algorithm for sparse precision matrix estimation via scaled Lasso, Sparsifying the least-squares approach to PCA: comparison of lasso and cardinality constraint, Weak multi-label learning with missing labels via instance granular discrimination, Biconvex Clustering, Nested alternating minimization with FISTA for non-convex and non-smooth optimization problems, The semiproximal SVM approach for multiple instance learning: a kernel-based computational study, Intrinsic spherical smoothing method based on generalized Bézier curves and sparsity inducing penalization, Convergence of an asynchronous block-coordinate forward-backward algorithm for convex composite optimization, Local linear convergence of proximal coordinate descent algorithm, A study of progressive hedging for stochastic integer programming, HV geometry for signal comparison, \(\ell_p\)-norm minimization for outlier-resistant elliptic positioning in \(\alpha\)-stable impulsive interference, Hierarchical ensemble Kalman methods with sparsity-promoting generalized gamma hyperpriors