Variance-Based Bregman Extragradient Algorithm with Line Search for Solving Stochastic Variational Inequalities
Abstract
The main purpose of this paper is to propose a variance-based Bregman extragradient algorithm with line search for solving stochastic variational inequalities, which is robust with respect an unknown Lipschitz constant. We prove the almost sure convergence of the algorithm by a more concise and effective method instead of using the supermartingale convergence theorem. Furthermore, we obtain not only the convergence rate with the gap function when is bounded, but also the same convergence rate in terms of the natural residual function when is unbounded. Under the Minty variational inequality condition, we derive the iteration complexity and the oracle complexity in both cases. Finally, some numerical results demonstrate the superiority of the proposed algorithm.
Cite
@article{arxiv.2208.14069,
title = {Variance-Based Bregman Extragradient Algorithm with Line Search for Solving Stochastic Variational Inequalities},
author = {Xian-Jun Long and Yue-Hong He and Nan-Jing Huang},
journal= {arXiv preprint arXiv:2208.14069},
year = {2022}
}