Saved in:
Bibliographic Details
Main Authors: Vankov, Daniil, Nedich, Angelia, Sankar, Lalitha
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.12334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909817065439232
author Vankov, Daniil
Nedich, Angelia
Sankar, Lalitha
author_facet Vankov, Daniil
Nedich, Angelia
Sankar, Lalitha
contents This paper focuses on solving a stochastic variational inequality (SVI) problem under relaxed smoothness assumption for a class of structured non-monotone operators. The SVI problem has attracted significant interest in the machine learning community due to its immediate application to adversarial training and multi-agent reinforcement learning. In many such applications, the resulting operators do not satisfy the smoothness assumption. To address this issue, we focus on a weaker generalized smoothness assumption called $α$-symmetric. Under $p$-quasi sharpness and $α$-symmetric assumptions on the operator, we study clipped projection (gradient descent-ascent) and clipped Korpelevich (extragradient) methods. For these clipped methods, we provide the first almost-sure convergence results without making any assumptions on the boundedness of either the stochastic operator or the stochastic samples. We also provide the first in-expectation unbiased convergence rate results for these methods under a relaxed smoothness assumption for $α\leq \frac{1}{2}$.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12334
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates
Vankov, Daniil
Nedich, Angelia
Sankar, Lalitha
Optimization and Control
This paper focuses on solving a stochastic variational inequality (SVI) problem under relaxed smoothness assumption for a class of structured non-monotone operators. The SVI problem has attracted significant interest in the machine learning community due to its immediate application to adversarial training and multi-agent reinforcement learning. In many such applications, the resulting operators do not satisfy the smoothness assumption. To address this issue, we focus on a weaker generalized smoothness assumption called $α$-symmetric. Under $p$-quasi sharpness and $α$-symmetric assumptions on the operator, we study clipped projection (gradient descent-ascent) and clipped Korpelevich (extragradient) methods. For these clipped methods, we provide the first almost-sure convergence results without making any assumptions on the boundedness of either the stochastic operator or the stochastic samples. We also provide the first in-expectation unbiased convergence rate results for these methods under a relaxed smoothness assumption for $α\leq \frac{1}{2}$.
title Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates
topic Optimization and Control
url https://arxiv.org/abs/2410.12334