A closed-measure approach to stochastic approximation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Stochastics: An International Journal of Probability and Stochastic Processes Année : 2023

A closed-measure approach to stochastic approximation

Résumé

This paper introduces a new method to tackle the issue of the almost sure convergence of stochastic approximation algorithms defined from a differential inclusion. Under the assumption of slowly decaying step-sizes, we establish that the set of essential accumulation points of the iterates belongs to the Birkhoff center associated with the differential inclusion. Unlike previous works, our results do not rely on the notion of asymptotic pseudotrajectories introduced by Benaı̈m–Hofbauer–Sorin, which is the predominant technique to address the convergence problem. They follow as a consequence of Young’s superposition principle for closed measures. This perspective bridges the gap between Young’s principle and the notion of invariant measure of set-valued dynamical systems introduced by Faure and Roth. Also, the proposed method allows to obtain sufficient conditions under which the velocities locally compensate around any essential accumulation point.
Fichier principal
Vignette du fichier
out.pdf (268.38 Ko) Télécharger le fichier
out (1).pdf (388.96 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04319492 , version 1 (02-12-2023)

Licence

Copyright (Tous droits réservés)

Identifiants

Citer

Pascal Bianchi, Rodolfo Rios-Zertuche. A closed-measure approach to stochastic approximation. Stochastics: An International Journal of Probability and Stochastic Processes, 2023, pp.1-23. ⟨10.1080/17442508.2024.2353278⟩. ⟨hal-04319492⟩
71 Consultations
31 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More