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

page 1

page 2

page 3

page 4

research
02/22/2021

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

Recent applications in machine learning have renewed the interest of the...
research
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...
research
10/05/2021

Convex-Concave Min-Max Stackelberg Games

Min-max optimization problems (i.e., min-max games) have been attracting...
research
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...
research
08/23/2023

A First-Order Algorithm for Decentralised Min-Max Problems

In this work, we consider a connected network of finitely many agents wo...
research
04/17/2020

On Regularity of Max-CSPs and Min-CSPs

We study approximability of regular constraint satisfaction problems, i....
research
06/09/2023

Specifying and Solving Robust Empirical Risk Minimization Problems Using CVXPY

We consider robust empirical risk minimization (ERM), where model parame...

Please sign up or login with your details

Forgot password? Click here to reset