Smooth monotone stochastic variational inequalities and saddle point problems: A survey

Aleksandr Beznosikov, Boris Polyak, Eduard Gorbunov, Dmitry Kovalev, Alexander Gasnikov

Research output: Contribution to journalArticlepeer-review

Abstract

This paper is a survey of methods for solving smooth, (strongly) monotone stochastic variational inequalities. To begin with, we present the deterministic foundation from which the stochastic methods eventually evolved. Then we review methods for the general stochastic formulation, and look at the finite-sum setup. The last parts of the paper are devoted to various recent (not necessarily stochastic) advances in algorithms for variational inequalities.
Original languageEnglish (US)
Pages (from-to)15-28
Number of pages14
JournalEuropean Mathematical Society Magazine
Issue number127
DOIs
StatePublished - Mar 22 2023

Bibliographical note

KAUST Repository Item: Exported on 2023-03-28
Acknowledgements: The work was supported by Russian Science Foundation (project No. 21-71-30005).

Fingerprint

Dive into the research topics of 'Smooth monotone stochastic variational inequalities and saddle point problems: A survey'. Together they form a unique fingerprint.

Cite this