Solving stochastic weak Minty variational inequalities without increasing batch size

Thomas Pethick, Olivier Fercoq, Puya Latafat, Panagiotis Patrinos, Volkan Cevher

Keywords: Variational inequalities, stochastic first-order methods, nonconvex-nonconcave, minimax

Abstract: This paper introduces a family of stochastic extragradient-type algorithms for a class of nonconvex-nonconcave problems characterized by the weak Minty variational inequality (MVI). Unlike existing results on extragradient methods in the monotone setting, employing diminishing stepsizes is no longer possible in the weak MVI setting. This has led to approaches such as increasing batch sizes per iteration which can however be prohibitively expensive. In contrast, our proposed methods involves two stepsizes and only requires one additional oracle evaluation per iteration. We show that it is possible to keep one fixed stepsize while it is only the second stepsize that is taken to be diminishing, making it interesting even in the monotone setting. Almost sure convergence is established and we provide a unified analysis for this family of schemes which contains a nonlinear generalization of the celebrated primal dual hybrid gradient algorithm.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Optimization (eg, convex and non-convex optimization)

TL;DR: Weak MVIs can be solved with only stochastic feedback using extragradient-like algorithms by introducing a bias-correction term

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2302.09029/code)