Skip to Main content Skip to Navigation
Journal articles

Concentration Inequalities for Mean Field Particle Models

Pierre del Moral 1, 2, * Emmanuel Rio 2, 3 
* Corresponding author
2 ALEA - Advanced Learning Evolutionary Algorithms
Inria Bordeaux - Sud-Ouest, UB - Université de Bordeaux, CNRS - Centre National de la Recherche Scientifique : UMR5251
Abstract : 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.
Document type :
Journal articles
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download
Contributor : Pierre Del Moral Connect in order to contact the contributor
Submitted on : Sunday, April 26, 2009 - 6:20:09 PM
Last modification on : Friday, February 4, 2022 - 3:22:46 AM
Long-term archiving on: : Saturday, November 26, 2016 - 8:31:56 AM


Files produced by the author(s)



Pierre del Moral, Emmanuel Rio. Concentration Inequalities for Mean Field Particle Models. Annals of Applied Probability, Institute of Mathematical Statistics (IMS), 2011, 21 (3), pp.1017-1052. ⟨10.1214/10-AAP716⟩. ⟨inria-00375134v3⟩



Record views


Files downloads