Optimality conditions for nonsmooth nonconvex-nonconcave min-max problems and generative adversarial networks
Optimization and Control
2022-03-22 v1
Abstract
This paper considers a class of nonsmooth nonconvex-nonconcave min-max problems in machine learning and games. We first provide sufficient conditions for the existence of global minimax points and local minimax points. Next, we establish the first-order and second-order optimality conditions for local minimax points by using directional derivatives. These conditions reduce to smooth min-max problems with Fr{\'e}chet derivatives. We apply our theoretical results to generative adversarial networks (GANs) in which two neural networks contest with each other in a game. Examples are used to illustrate applications of the new theory for training GANs.
Cite
@article{arxiv.2203.10914,
title = {Optimality conditions for nonsmooth nonconvex-nonconcave min-max problems and generative adversarial networks},
author = {Jie Jiang and Xiaojun Chen},
journal= {arXiv preprint arXiv:2203.10914},
year = {2022}
}