English

Two trust region type algorithms for solving nonconvex-strongly concave minimax problems

Optimization and Control 2024-02-16 v1 Machine Learning Machine Learning

Abstract

In this paper, we propose a Minimax Trust Region (MINIMAX-TR) algorithm and a Minimax Trust Region Algorithm with Contractions and Expansions(MINIMAX-TRACE) algorithm for solving nonconvex-strongly concave minimax problems. Both algorithms can find an (ϵ,ϵ)(\epsilon, \sqrt{\epsilon})-second order stationary point(SSP) within O(ϵ1.5)\mathcal{O}(\epsilon^{-1.5}) iterations, which matches the best well known iteration complexity.

Keywords

Cite

@article{arxiv.2402.09807,
  title  = {Two trust region type algorithms for solving nonconvex-strongly concave minimax problems},
  author = {Tongliang Yao and Zi Xu},
  journal= {arXiv preprint arXiv:2402.09807},
  year   = {2024}
}
R2 v1 2026-06-28T14:49:23.077Z