Saved in:
Bibliographic Details
Main Authors: Chakraborty, Abhishek, Nedić, Angelia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.00635
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917787186757632
author Chakraborty, Abhishek
Nedić, Angelia
author_facet Chakraborty, Abhishek
Nedić, Angelia
contents We consider the mirror-prox algorithm for solving monotone Variational Inequality (VI) problems. As the mirror-prox algorithm is not practically implementable, except in special instances of VIs (such as affine VIs), we consider its implementation with Popov method updates. We provide convergence rate analysis of our proposed method for a monotone VI with a Lipschitz continuous mapping. We establish a convergence rate of $O(1/t)$, in terms of the number $t$ of iterations, for the dual gap function. Simulations on a two player matrix game corroborate our findings.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00635
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Popov Mirror-Prox for solving Variational Inequalities
Chakraborty, Abhishek
Nedić, Angelia
Optimization and Control
We consider the mirror-prox algorithm for solving monotone Variational Inequality (VI) problems. As the mirror-prox algorithm is not practically implementable, except in special instances of VIs (such as affine VIs), we consider its implementation with Popov method updates. We provide convergence rate analysis of our proposed method for a monotone VI with a Lipschitz continuous mapping. We establish a convergence rate of $O(1/t)$, in terms of the number $t$ of iterations, for the dual gap function. Simulations on a two player matrix game corroborate our findings.
title Popov Mirror-Prox for solving Variational Inequalities
topic Optimization and Control
url https://arxiv.org/abs/2404.00635