Salvato in:
Dettagli Bibliografici
Autori principali: Vankov, Daniil, Nedich, Angelia, Sankar, Lalitha
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2402.05691
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909099090771968
author Vankov, Daniil
Nedich, Angelia
Sankar, Lalitha
author_facet Vankov, Daniil
Nedich, Angelia
Sankar, Lalitha
contents Variational Inequality (VI) problems have attracted great interest in the machine learning (ML) community due to their application in adversarial and multi-agent training. Despite its relevance in ML, the oft-used strong-monotonicity and Lipschitz continuity assumptions on VI problems are restrictive and do not hold in practice. To address this, we relax smoothness and monotonicity assumptions and study structured non-monotone generalized smoothness. The key idea of our results is in adaptive stepsizes. We prove the first-known convergence results for solving generalized smooth VIs for the three popular methods, namely, projection, Korpelevich, and Popov methods. Our convergence rate results for generalized smooth VIs match or improve existing results on smooth VIs. We present numerical experiments that support our theoretical guarantees and highlight the efficiency of proposed adaptive stepsizes.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05691
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Methods for Variational Inequalities under Relaxed Smoothness Assumption
Vankov, Daniil
Nedich, Angelia
Sankar, Lalitha
Optimization and Control
Variational Inequality (VI) problems have attracted great interest in the machine learning (ML) community due to their application in adversarial and multi-agent training. Despite its relevance in ML, the oft-used strong-monotonicity and Lipschitz continuity assumptions on VI problems are restrictive and do not hold in practice. To address this, we relax smoothness and monotonicity assumptions and study structured non-monotone generalized smoothness. The key idea of our results is in adaptive stepsizes. We prove the first-known convergence results for solving generalized smooth VIs for the three popular methods, namely, projection, Korpelevich, and Popov methods. Our convergence rate results for generalized smooth VIs match or improve existing results on smooth VIs. We present numerical experiments that support our theoretical guarantees and highlight the efficiency of proposed adaptive stepsizes.
title Adaptive Methods for Variational Inequalities under Relaxed Smoothness Assumption
topic Optimization and Control
url https://arxiv.org/abs/2402.05691