Mean-field limits for Consensus-Based Optimization and Sampling - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2023

Mean-field limits for Consensus-Based Optimization and Sampling

Résumé

For algorithms based on interacting particle systems that admit a mean-field description, convergence analysis is often more accessible at the mean-field level. In order to transpose convergence results obtained at the mean-field level to the finite ensemble size setting, it is desirable to show that the particle dynamics converge in an appropriate sense to the corresponding mean-field dynamics. In this paper, we prove quantitative mean-field limit results for two related interacting particle systems: Consensus-Based Optimization and Consensus-Based Sampling. Our approach extends Sznitman's classical argument: in order to circumvent issues related to the lack of global Lipschitz continuity of the coefficients, we discard an event of small probability, the contribution of which is controlled using moment estimates for the particle systems.
Fichier principal
Vignette du fichier
2312.07373v2.pdf (559.05 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04346646 , version 1 (15-12-2023)
hal-04346646 , version 2 (30-08-2024)

Licence

Identifiants

Citer

Nicolai Jurek Gerber, Franca Hoffmann, Urbain Vaes. Mean-field limits for Consensus-Based Optimization and Sampling. 2024. ⟨hal-04346646v2⟩
71 Consultations
54 Téléchargements

Altmetric

Partager

More