Variance-Based Bregman Extragradient Algorithm with Line Search for Solving Stochastic Variational Inequalities
Xian-Jun Long, Yue-Hong He, Nan-Jing Huang

TL;DR
This paper introduces a variance-based Bregman extragradient algorithm with line search for stochastic variational inequalities, achieving robust convergence without knowing the Lipschitz constant and providing optimal convergence rates.
Contribution
It proposes a novel variance-based extragradient method with line search that ensures convergence under unknown Lipschitz constants and establishes optimal convergence and complexity rates.
Findings
Almost sure convergence proved using a new method.
Achieves $ ext{O}(1/k)$ convergence rate for bounded sets.
Demonstrates superiority through numerical experiments.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPoint processes and geometric inequalities · Optimization and Variational Analysis · Risk and Portfolio Optimization
