English

Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems

Optimization and Control 2024-01-26 v5 Machine Learning Machine Learning

Abstract

In this paper, we study zeroth-order algorithms for nonconvex-concave minimax problems, which have attracted widely attention in machine learning, signal processing and many other fields in recent years. We propose a zeroth-order alternating randomized gradient projection (ZO-AGP) algorithm for smooth nonconvex-concave minimax problems, and its iteration complexity to obtain an ε\varepsilon-stationary point is bounded by O(ε4)\mathcal{O}(\varepsilon^{-4}), and the number of function value estimation is bounded by O(dx+dy)\mathcal{O}(d_{x}+d_{y}) per iteration. Moreover, we propose a zeroth-order block alternating randomized proximal gradient algorithm (ZO-BAPG) for solving block-wise nonsmooth nonconvex-concave minimax optimization problems, and the iteration complexity to obtain an ε\varepsilon-stationary point is bounded by O(ε4)\mathcal{O}(\varepsilon^{-4}) and the number of function value estimation per iteration is bounded by O(Kdx+dy)\mathcal{O}(K d_{x}+d_{y}). To the best of our knowledge, this is the first time that zeroth-order algorithms with iteration complexity gurantee are developed for solving both general smooth and block-wise nonsmooth nonconvex-concave minimax problems. Numerical results on data poisoning attack problem and distributed nonconvex sparse principal component analysis problem validate the efficiency of the proposed algorithms.

Keywords

Cite

@article{arxiv.2108.00473,
  title  = {Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems},
  author = {Zi Xu and Ziqi Wang and Jingjing Shen and Yuhong Dai},
  journal= {arXiv preprint arXiv:2108.00473},
  year   = {2024}
}
R2 v1 2026-06-24T04:43:47.115Z