English

Calm local optimality for nonconvex-nonconcave minimax problems

Optimization and Control 2023-07-03 v1

Abstract

Nonconvex-nonconcave minimax problems have found numerous applications in various fields including machine learning. However, questions remain about what is a good surrogate for local minimax optimum and how to characterize the minimax optimality. Recently Jin, Netrapalli, and Jordan (ICML 2020) introduced a concept of local minimax point and derived optimality conditions for the smooth and unconstrained case. In this paper, we introduce the concept of calm local minimax point, which is a local minimax point with a calm radius function. With the extra calmness property we obtain first and second-order sufficient and necessary optimality conditions for a very general class of nonsmooth nonconvex-nonconcave minimax problem. Moreover we show that the calm local minimax optimality and the local minimax optimality coincide under a weak sufficient optimality condition for the maximization problem. This equivalence allows us to derive stronger optimality conditions under weaker assumptions for local minimax optimality.

Keywords

Cite

@article{arxiv.2306.17443,
  title  = {Calm local optimality for nonconvex-nonconcave minimax problems},
  author = {Xiaoxiao Ma and Wei Yao and Jane J. Ye and Jin Zhang},
  journal= {arXiv preprint arXiv:2306.17443},
  year   = {2023}
}

Comments

40 pages

R2 v1 2026-06-28T11:18:40.434Z