Online Min-max Optimization: Nonconvexity, Nonstationarity, and Dynamic Regret

Yu Huang, Yuan Cheng, Yingbin Liang, Longbo Huang

Keywords: Online Optimization, Nonconvex, Minimax

Abstract: Online min-max optimization has recently gained considerable interest due to its rich applications to game theory, multi-agent reinforcement learning, online robust learning, etc. Theoretical understanding in this field has been mainly focused on convex-concave settings. Online min-max optimization with nonconvex geometries, which captures various online deep learning problems, has yet been studied so far. In this paper, we make the first effort and investigate online nonconvex-strongly-concave min-max optimization in the nonstationary environment. We first introduce a natural notion of local Nash equilibrium (NE)-regret, and then propose a novel algorithm coined SODA to achieve the optimal regret. We further generalize our study to the setting with stochastic first-order feedback, and show that a variation of SODA can also achieve the same optimal regret in expectation. Our theoretical results and the superior performance of the proposed method are further validated by empirical experiments. To our best knowledge, this is the first exploration of efficient online nonconvex min-max optimization.

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: We study the online nonconvex-strongly-concave min-max optimization in the nonstationary environment and propose efficient algorithms with optimal theoretical guarantees under novel notion of regret