Concentration Inequalities for Mean Field Particle Models - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2009

Concentration Inequalities for Mean Field Particle Models

Résumé

This article is concerned with the fluctuations and the concentration properties of a general class of discrete generation and mean field particle interpretations of non linear measure valued processes. We combine an original stochastic perturbation analysis with a concentration analysis for triangular arrays of conditionally independent random sequences, which may be of independent interest. Under some additional stability properties of the limiting measure valued processes, uniform concentration properties with respect to the time parameter are also derived. The concentration inequalities presented here generalize the classical Hoeffding, Bernstein and Bennett inequalities for independent random sequences to interacting particle systems, yielding very new results for this class of models. We illustrate these results in the context of McKean Vlasov type diffusion models, McKean collision type models of gases, and of a class of Feynman-Kac distribution flows arising in stochastic engineering sciences and in molecular chemistry.
Fichier principal
Vignette du fichier
RR-concentration.pdf (333.11 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

inria-00375134 , version 1 (13-04-2009)
inria-00375134 , version 2 (14-04-2009)
inria-00375134 , version 3 (26-04-2009)

Identifiants

  • HAL Id : inria-00375134 , version 1

Citer

Pierre del Moral, Emmanuel Rio. Concentration Inequalities for Mean Field Particle Models. [Research Report] 2009, pp.29. ⟨inria-00375134v1⟩

Collections

INRIA-RRRT
670 Consultations
318 Téléchargements

Partager

Gmail Facebook X LinkedIn More