March 15, 2024Open Access

Randomly Activated Proximal Methods for Nonsmooth Convex Minimization

Key Points

Key points are not available for this paper at this time.

Abstract

We propose stochastic algorithms for solving large scale nonsmooth convex composite minimization problems. They activate at each iteration blocks of randomly selected proximity operators and achieve almost sure convergence of the iterates to a solution without any regularity assumptions. Numerical applications to data analysis problems are provided.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Combettes et al. (Fri,) studied this question.

synapsesocial.com/papers/68e73ed6b6db6435876b88c6 https://doi.org/https://doi.org/10.48550/arxiv.2403.10673

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Alternating and Parallel Proximal Gradient Methods for Nonsmooth, Nonconvex Minimax: A Unified Convergence Analysis2024 · 4 citations
2A Proximal-Gradient Method for Constrained Optimization2024
3An efficient active-set method with applications to sparse approximations and risk minimization2024
4An implementable proximal-type method for computing critical points to minimization problems with a nonsmooth and nonconvex constraint2024
5Stochastic alternating structure-adapted proximal gradient descent method with variance reduction for nonconvex nonsmooth optimization2024 · 4 citations

Bookmark

View Full Paper