Saved in:
Bibliographic Details
Main Authors: Zhong-bao, Wang, Zhong-cheng, Zhang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.16007
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917095510376448
author Zhong-bao, Wang
Zhong-cheng, Zhang
author_facet Zhong-bao, Wang
Zhong-cheng, Zhang
contents In this paper, we address variational inequalities (VI) with a finite sum structure by proposing a novel single-loop variance-reduced algorithm that incorporates the Bregman distance. Under the monotone setting, we establish the almost sure convergence of the proposed algorithm and prove that it achieves the optimal complexity of $\mathcal{O}\left(\frac{\sqrt{M}}{\varepsilon }\right)$ for finding an $\varepsilon$-gap. Furthermore, under the non-monotone setting, we derive a complexity of $\mathcal{O}\left(\frac{1}{\varepsilon^2 }\right)$ of the algorithm. Our proposed method yields complexity results that either match or improve the state-of-the-art complexity bounds reported in existing literature. Notably, this work is the first to rigorously establish the linear convergence rate of the algorithm for solving finite-sum variational inequalities in Bregman setups. Finally, we report two numerical experiments to validate the effectiveness and practical performance of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16007
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Single-loop variance reduction methods in Bregman setups for finite-sum structured variational inequalities
Zhong-bao, Wang
Zhong-cheng, Zhang
Optimization and Control
90C15
In this paper, we address variational inequalities (VI) with a finite sum structure by proposing a novel single-loop variance-reduced algorithm that incorporates the Bregman distance. Under the monotone setting, we establish the almost sure convergence of the proposed algorithm and prove that it achieves the optimal complexity of $\mathcal{O}\left(\frac{\sqrt{M}}{\varepsilon }\right)$ for finding an $\varepsilon$-gap. Furthermore, under the non-monotone setting, we derive a complexity of $\mathcal{O}\left(\frac{1}{\varepsilon^2 }\right)$ of the algorithm. Our proposed method yields complexity results that either match or improve the state-of-the-art complexity bounds reported in existing literature. Notably, this work is the first to rigorously establish the linear convergence rate of the algorithm for solving finite-sum variational inequalities in Bregman setups. Finally, we report two numerical experiments to validate the effectiveness and practical performance of our method.
title Single-loop variance reduction methods in Bregman setups for finite-sum structured variational inequalities
topic Optimization and Control
90C15
url https://arxiv.org/abs/2511.16007