English

Solving Non-Convex Non-Differentiable Min-Max Games using Proximal Gradient Method

Optimization and Control 2020-03-19 v1 Computer Science and Game Theory Machine Learning Machine Learning

Abstract

Min-max saddle point games appear in a wide range of applications in machine leaning and signal processing. Despite their wide applicability, theoretical studies are mostly limited to the special convex-concave structure. While some recent works generalized these results to special smooth non-convex cases, our understanding of non-smooth scenarios is still limited. In this work, we study special form of non-smooth min-max games when the objective function is (strongly) convex with respect to one of the player's decision variable. We show that a simple multi-step proximal gradient descent-ascent algorithm converges to ϵ\epsilon-first-order Nash equilibrium of the min-max game with the number of gradient evaluations being polynomial in 1/ϵ1/\epsilon. We will also show that our notion of stationarity is stronger than existing ones in the literature. Finally, we evaluate the performance of the proposed algorithm through adversarial attack on a LASSO estimator.

Keywords

Cite

@article{arxiv.2003.08093,
  title  = {Solving Non-Convex Non-Differentiable Min-Max Games using Proximal Gradient Method},
  author = {Babak Barazandeh and Meisam Razaviyayn},
  journal= {arXiv preprint arXiv:2003.08093},
  year   = {2020}
}
R2 v1 2026-06-23T14:18:21.833Z