ICLR 2024poster6 citations
Two-timescale Extragradient for Finding Local Minimax Points
Jiseok Chae, Kyuwon Kim, Donghwan Kim
Abstract
Minimax problems are notoriously challenging to optimize. However, we present that the two-timescale extragradient method can be a viable solution. By utilizing dynamical systems theory, we show that it converges to points that satisfy the second-order necessary condition of local minimax points, under mild conditions that the two-timescale gradient descent ascent fails to work. This work provably improves upon all previous results on finding local minimax points, by eliminating a crucial assumption that the Hessian with respect to the maximization variable is nondegenerate.
Minimax optimizationNonconvex-nonconcave optimizationExtragradient methodDynamical systems
BibTeX
@inproceedings{
chae2024twotimescale,
title={Two-timescale Extragradient for Finding Local Minimax Points},
author={Jiseok Chae and Kyuwon Kim and Donghwan Kim},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=6CIGhcJYJH}
}