The backtrack Hölder gradient method with application to min-max and min-min problems
Open Journal of Mathematical Optimization · 2023
DOI: 10.5802/ojmo.24 ↗Kurz gefasst
Fachartikel in der Zeitschrift Open Journal of Mathematical Optimization, 2023. Verfasst von Jérôme Bolte und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
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 – the backtrack Hölder algorithm applicable to many optimization problems. Our approach takes advantage of hidden regularity properties and allows us, in particular, 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 Generative Adversarial Network (GAN) problems obtaining promising numerical results. It is worthwhile mentioning that a byproduct of our approach is a simple recipe for general Hölderian backtracking optimization.
Zitieren
APA
Bolte, J., Glaudin, L., Pauwels, E., & Serrurier, M. (2023). The backtrack Hölder gradient method with application to min-max and min-min problems. Open Journal of Mathematical Optimization. https://doi.org/10.5802/ojmo.24
Vancouver
Bolte J, Glaudin L, Pauwels E, Serrurier M. The backtrack Hölder gradient method with application to min-max and min-min problems. Open Journal of Mathematical Optimization. 2023. doi:10.5802/ojmo.24
BibTeX
@article{Bolte2023,
author = {Bolte, Jérôme and Glaudin, Lilian and Pauwels, Edouard and Serrurier, Mathieu},
title = {The backtrack Hölder gradient method with application to min-max and min-min problems},
journal = {Open Journal of Mathematical Optimization},
year = {2023},
doi = {10.5802/ojmo.24}
}
EUVIMED