Minibatch Forward-Backward-Forward Methods for Solving Stochastic Variational Inequalities release_z4ty7wgazbf6ngxrgoflo6dk54

by Radu Ioan Bot, Panayotis Mertikopoulos, Mathias Staudigl, Vuong Phan

Published in Stochastic Systems by Institute for Operations Research and the Management Sciences (INFORMS).

2021  

Abstract

We develop a new stochastic algorithm for solving pseudomonotone stochastic variational inequalities. Our method builds on Tseng's forward-backward-forward algorithm, which is known in the deterministic literature to be a valuable alternative to Korpelevich's extragradient method when solving variational inequalities over a convex and closed set governed by pseudomonotone Lipschitz continuous operators. The main computational advantage of Tseng's algorithm is that it relies only on a single projection step and two independent queries of a stochastic oracle. Our algorithm incorporates a minibatch sampling mechanism and leads to almost sure convergence to an optimal solution. To the best of our knowledge, this is the first stochastic look-ahead algorithm achieving this by using only a single projection at each iteration.
In application/xml+jats format

Archived Files and Locations

application/pdf  1.5 MB
file_vmwj6ijvi5e4niwqd5uxam4vyu
cris.maastrichtuniversity.nl (web)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2021-02-25
Language   en ?
Container Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  1946-5238
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: a64b4519-2eb3-48ef-a9d4-0b291208335e
API URL: JSON