Linear convergence of prox-SVRG method for separable non-smooth convex optimization problems under bounded metric subregularity

DOI10.1007/S10957-021-01978-WzbMATH Open1487.90530OpenAlexW4205999994MaRDI QIDQ2115253FDOQ2115253

Jin Zhang, Xi-De Zhu

Publication date: 15 March 2022

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

Full work available at URL: https://doi.org/10.1007/s10957-021-01978-w

Recommendations

• Variable metric proximal stochastic variance reduced gradient methods for nonconvex nonsmooth optimization
• scientific article; zbMATH DE number 7404502
• Asymptotic estimates for \(r\)-Whitney numbers of the second kind
• On the linear convergence of a proximal gradient method for a class of nonsmooth convex minimization problems
• Variational analysis perspective on linear convergence of some first order methods for nonsmooth convex optimization problems

zbMATH Keywords

calmnesslinear convergencebounded metric subregularityproximal stochastic variance-reduced gradientrandomized block-coordinate proximal gradient

Mathematics Subject Classification ID

Convex programming (90C25) Methods of reduced gradient type (90C52)

Cites Work

• Title not available (Why is that?)
• Variational Analysis
• Model Selection and Estimation in Regression with Grouped Variables
• The Group Lasso for Logistic Regression
• Convex Analysis
• A coordinate gradient descent method for nonsmooth separable minimization
• Techniques of variational analysis
• Recovery Algorithms for Vector-Valued Data with Joint Sparsity Constraints
• Strongly Regular Generalized Equations
• Approximation accuracy, gradient methods, and error bound for structured convex optimization
• Sparse regression using mixed norms
• Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
• Optimization in high dimensions via accelerated, parallel, and proximal coordinate descent
• Efficiency of coordinate descent methods on huge-scale optimization problems
• Parallel Random Coordinate Descent Method for Composite Minimization: Convergence Analysis and Error Bounds
• Lipschitz Behavior of Solutions to Convex Minimization Problems
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• Stability Theory for Systems of Inequalities. Part I: Linear Systems
• On the Linear Convergence of Descent Methods for Convex Essentially Smooth Minimization
• Characterization of metric regularity of subdifferentials
• Necessary Optimality Conditions for Optimization Problems with Variational Inequality Constraints
• Metric subregularity of the convex subdifferential in Banach spaces
• New Constraint Qualifications for Mathematical Programs with Equilibrium Constraints via Variational Analysis
• Regularity and conditioning of solution mappings in variational analysis
• Random block coordinate descent methods for linearly constrained optimization over networks
• Metric Subregularity of Piecewise Linear Multifunctions and Applications to Piecewise Linear Multiobjective Optimization
• Title not available (Why is that?)
• Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
• A unified approach to error bounds for structured convex optimization problems
• Title not available (Why is that?)
• Variational analysis perspective on linear convergence of some first order methods for nonsmooth convex optimization problems

Cited In (1)

• Variance reduction techniques for stochastic proximal point algorithms

Uses Software

• Saga

This page was built for publication: Linear convergence of prox-SVRG method for separable non-smooth convex optimization problems under bounded metric subregularity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2115253)