English

Accelerated Primal-dual Scheme for a Class of Stochastic Nonconvex-concave Saddle Point Problems

Optimization and Control 2023-09-12 v2

Abstract

Stochastic nonconvex-concave min-max saddle point problems appear in many machine learning and control problems including distributionally robust optimization, generative adversarial networks, and adversarial learning. In this paper, we consider a class of nonconvex saddle point problems where the objective function satisfies the Polyak-{\L}ojasiewicz condition with respect to the minimization variable and it is concave with respect to the maximization variable. The existing methods for solving nonconvex-concave saddle point problems often suffer from slow convergence and/or contain multiple loops. Our main contribution lies in proposing a novel single-loop accelerated primal-dual algorithm with new convergence rate results appearing for the first time in the literature, to the best of our knowledge. In particular, in the stochastic regime, we demonstrate a convergence rate of O(ϵ4)\mathcal O(\epsilon^{-4}) to find an ϵ\epsilon-gap solution which can be improved to O(ϵ2)\mathcal O(\epsilon^{-2}) in deterministic setting.

Keywords

Cite

@article{arxiv.2303.00211,
  title  = {Accelerated Primal-dual Scheme for a Class of Stochastic Nonconvex-concave Saddle Point Problems},
  author = {Morteza Boroun and Zeinab Alizadeh and Afrooz Jalilzadeh},
  journal= {arXiv preprint arXiv:2303.00211},
  year   = {2023}
}