Skip to yearly menu bar Skip to main content

Workshop: OPT 2022: Optimization for Machine Learning

Accelerated Algorithms for Monotone Inclusion and Constrained Nonconvex-Nonconcave Min-Max Optimization

Yang Cai · Argyris Oikonomou · Weiqiang Zheng

Abstract: We study monotone inclusions and monotone variational inequalities, as well as their generalizations to non-monotone settings. We first show that the \emph{Extra Anchored Gradient (EAG)} algorithm, originally proposed by [Yoon and Ryu, 2021] for unconstrained convex-concave min-max optimization, can be applied to solve the more general problem of Lipschitz monotone inclusion. More specifically, we prove that the EAG solves Lipschitz monotone inclusion problems with an \emph{accelerated convergence rate} of $O(\frac{1}{T})$, which is \emph{optimal among all first-order methods} [Diakonikolas, 2020, Yoon and Ryu, 2021]. Our second result is an {accelerated forward-backward splitting algorithm (AS),} which not only achieves the accelerated $O(\frac{1}{T})$ convergence rate for all monotone inclusion problems, but also exhibits the same accelerated rate for a family of general (non-monotone) inclusion problems that concern negative comonotone operators. As a special case of our second result, AS enjoys the $O(\frac{1}{T})$ convergence rate for solving a non-trivial class of nonconvex-nonconcave min-max optimization problems. Our analyses are based on simple potential function arguments, which might be useful for analysing other accelerated algorithms.

Chat is not available.