Well-posedness and mean-field limit estimate of a consensus-based algorithm for min-max problems

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Hui, Warnett, Jethro
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918336655261696
author Huang, Hui
Warnett, Jethro
author_facet Huang, Hui
Warnett, Jethro
contents The recent work arXiv:2407.17373 proposes a derivative-free consensus-based particle method that computes global solutions to nonconvex-nonconcave min-max problems and establishes global exponential convergence in the sense of the mean-field law. This paper aims to address the theoretical gaps in arXiv:2407.17373, specifically by providing a quantitative estimate of the mean-field limit with respect to the number of particles, as well as establishing the well-posedness of both the finite particle model and the corresponding mean-field dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12886
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Well-posedness and mean-field limit estimate of a consensus-based algorithm for min-max problems
Huang, Hui
Warnett, Jethro
Optimization and Control
65C35, 65K05, 90C56, 35Q90, 35Q83
The recent work arXiv:2407.17373 proposes a derivative-free consensus-based particle method that computes global solutions to nonconvex-nonconcave min-max problems and establishes global exponential convergence in the sense of the mean-field law. This paper aims to address the theoretical gaps in arXiv:2407.17373, specifically by providing a quantitative estimate of the mean-field limit with respect to the number of particles, as well as establishing the well-posedness of both the finite particle model and the corresponding mean-field dynamics.
title Well-posedness and mean-field limit estimate of a consensus-based algorithm for min-max problems
topic Optimization and Control
65C35, 65K05, 90C56, 35Q90, 35Q83
url https://arxiv.org/abs/2602.12886