Adaptive extra-gradient methods for min-max optimization and games

by   Kimon Antonakopoulos, et al.

We present a new family of min-max optimization algorithms that automatically exploit the geometry of the gradient data observed at earlier iterations to perform more informative extra-gradient steps in later ones. Thanks to this adaptation mechanism, the proposed method automatically detects whether the problem is smooth or not, without requiring any prior tuning by the optimizer. As a result, the algorithm simultaneously achieves order-optimal convergence rates, i.e., it converges to an ε-optimal solution within 𝒪(1/ε) iterations in smooth problems, and within 𝒪(1/ε^2) iterations in non-smooth ones. Importantly, these guarantees do not require any of the standard boundedness or Lipschitz continuity conditions that are typically assumed in the literature; in particular, they apply even to problems with singularities (such as resource allocation problems and the like). This adaptation is achieved through the use of a geometric apparatus based on Finsler metrics and a suitably chosen mirror-prox template that allows us to derive sharp convergence rates for the methods at hand.



There are no comments yet.


page 6


Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements

We propose a new family of adaptive first-order methods for a class of c...

Last-iterate convergence rates for min-max optimization

We study the problem of finding min-max solutions for smooth two-input o...

Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems

There are much recent interests in solving noncovnex min-max optimizatio...

A Hölderian backtracking method for min-max and min-min problems

We present a new algorithm to solve min-max or min-min problems out of t...

Adaptive and Universal Single-gradient Algorithms for Variational Inequalities

Variational inequalities with monotone operators capture many problems o...

Convergence Behaviour of Some Gradient-Based Methods on Bilinear Zero-Sum Games

Min-max formulations have attracted great attention in the ML community ...

Convergence analysis of direct minimization and self-consistent iterations

This article is concerned with the numerical solution of subspace optimi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.