English

On the Convergence of Proximal Algorithms for Weakly-convex Min-max Optimization

Optimization and Control 2026-03-31 v1

Abstract

We study alternating first-order algorithms with no inner loops for solving nonconvex-strongly-concave min-max problems. We show the convergence of the alternating gradient descent--ascent algorithm method by proposing a substantially simplified proof compared to previous ones. It allows us to enlarge the set of admissible step-sizes. Building on this general reformulation, we also prove the convergence of a doubly proximal algorithm in the weakly convex-strongly concave setting. Finally, we show how this new result opens the way to new applications of min-max optimization algorithms for solving regularized imaging inverse problems with neural networks in a plug-and-play manner.

Keywords

Cite

@article{arxiv.2603.28484,
  title  = {On the Convergence of Proximal Algorithms for Weakly-convex Min-max Optimization},
  author = {Guido Tapia-Riera and Camille Castera and Nicolas Papadakis},
  journal= {arXiv preprint arXiv:2603.28484},
  year   = {2026}
}
R2 v1 2026-07-01T11:44:11.802Z