English

Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $\mathcal{O}(1/k^2)$ Rate on Squared Gradient Norm

Optimization and Control 2021-06-11 v2

Abstract

In this work, we study the computational complexity of reducing the squared gradient magnitude for smooth minimax optimization problems. First, we present algorithms with accelerated O(1/k2)\mathcal{O}(1/k^2) last-iterate rates, faster than the existing O(1/k)\mathcal{O}(1/k) or slower rates for extragradient, Popov, and gradient descent with anchoring. The acceleration mechanism combines extragradient steps with anchoring and is distinct from Nesterov's acceleration. We then establish optimality of the O(1/k2) \mathcal{O}(1/k^2) rate through a matching lower bound.

Keywords

Cite

@article{arxiv.2102.07922,
  title  = {Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $\mathcal{O}(1/k^2)$ Rate on Squared Gradient Norm},
  author = {TaeHo Yoon and Ernest K. Ryu},
  journal= {arXiv preprint arXiv:2102.07922},
  year   = {2021}
}

Comments

Published at ICML 2021 as a long talk

R2 v1 2026-06-23T23:11:44.640Z