Stochastic Proximal Point Methods for Monotone Inclusions under Expected Similarity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sadiev, Abdurakhmon, Condat, Laurent, Richtárik, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913359716155392
author Sadiev, Abdurakhmon
Condat, Laurent
Richtárik, Peter
author_facet Sadiev, Abdurakhmon
Condat, Laurent
Richtárik, Peter
contents Monotone inclusions have a wide range of applications, including minimization, saddle-point, and equilibria problems. We introduce new stochastic algorithms, with or without variance reduction, to estimate a root of the expectation of possibly set-valued monotone operators, using at every iteration one call to the resolvent of a randomly sampled operator. We also introduce a notion of similarity between the operators, which holds even for discontinuous operators. We leverage it to derive linear convergence results in the strongly monotone setting.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14255
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stochastic Proximal Point Methods for Monotone Inclusions under Expected Similarity
Sadiev, Abdurakhmon
Condat, Laurent
Richtárik, Peter
Optimization and Control
Monotone inclusions have a wide range of applications, including minimization, saddle-point, and equilibria problems. We introduce new stochastic algorithms, with or without variance reduction, to estimate a root of the expectation of possibly set-valued monotone operators, using at every iteration one call to the resolvent of a randomly sampled operator. We also introduce a notion of similarity between the operators, which holds even for discontinuous operators. We leverage it to derive linear convergence results in the strongly monotone setting.
title Stochastic Proximal Point Methods for Monotone Inclusions under Expected Similarity
topic Optimization and Control
url https://arxiv.org/abs/2405.14255