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

07/17/2020
by   Jérôme Bolte, et al.
0

We present a new algorithm to solve min-max or min-min problems out of the convex world. We use rigidity assumptions, ubiquitous in learning, making our method applicable to many optimization problems. Our approach takes advantage of hidden regularity properties and allows us to devise a simple algorithm of ridge type. An original feature of our method is to come with automatic step size adaptation which departs from the usual overly cautious backtracking methods. In a general framework, we provide convergence theoretical guarantees and rates. We apply our findings on simple GAN problems obtaining promising numerical results.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/22/2021

Direct-Search for a Class of Stochastic Min-Max Problems

Recent applications in machine learning have renewed the interest of the...
04/26/2021

Solving a class of non-convex min-max games using adaptive momentum methods

Adaptive momentum methods have recently attracted a lot of attention for...
10/05/2021

Convex-Concave Min-Max Stackelberg Games

Min-max optimization problems (i.e., min-max games) have been attracting...
11/14/2019

{-1,0,1}-APSP and (min,max)-Product Problems

In the {-1,0,1}-APSP problem the goal is to compute all-pairs shortest p...
07/05/2020

Novel min-max reformulations of Linear Inverse Problems

In this article, we dwell into the class of so-called ill-posed Linear I...
10/22/2020

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

We present a new family of min-max optimization algorithms that automati...
03/13/2018

Closure Operators and Spam Resistance for PageRank

We study the spammablility of ranking functions on the web. Although gra...
This week in AI

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