The Annals of Applied Probability

A Berry–Esseen theorem for Feynman–Kac and interacting particle models

Pierre Del Moral and Samy Tindel

Full-text: Open access


In this paper we investigate the speed of convergence of the fluctuations of a general class of Feynman–Kac particle approximation models. We design an original approach based on new Berry–Esseen type estimates for abstract martingale sequences combined with original exponential concentration estimates of interacting processes. These results extend the corresponding statements in the classical theory and apply to a class of branching and genealogical path-particle models arising in nonlinear filtering literature as well as in statistical physics and biology.

Article information

Ann. Appl. Probab., Volume 15, Number 1B (2005), 941-962.

First available in Project Euclid: 1 February 2005

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 65C05: Monte Carlo methods 65C35: Stochastic particle methods [See also 82C80] 65C40: Computational Markov chains

Berry–Esseen theorem Feyman–Kac models interacting particle systems


Del Moral, Pierre; Tindel, Samy. A Berry–Esseen theorem for Feynman–Kac and interacting particle models. Ann. Appl. Probab. 15 (2005), no. 1B, 941--962. doi:10.1214/105051604000000792.

Export citation


  • Del Moral, P. (1998). Measure valued processes and interacting particle systems. Application to nonlinear filtering problems. Ann. Appl. Probab. 8 438–495.
  • Del Moral, P. and Guionnet, A. (1999). Central limit theorem for nonlinear filtering and interacting particle systems. Ann. Appl. Probab. 9 275–297.
  • Del Moral, P. and Jacod, J. (2002). The Monte Carlo method for filtering with discrete time observations. Central limit theorems. In Numerical Methods and Stochastics (T. J. Lyons and T. S. Salisbury, eds.) 29–53. Amer. Math. Soc., Providence, RI.
  • Del Moral, P. and Ledoux, M. (2000). Convergence of empirical processes for interacting particle systems with applications to nonlinear filtering. J. Theoret. Probab. 13 225–257.
  • Del Moral, P. and Miclo, L. (2000). Branching and interacting particle systems approximations of Feynman–Kac formulae with applications to non-linear filtering. Séminaire de Probabilités XXXIV. Lecture Notes in Math. 1729 1–145. Springer, New York.
  • Del Moral, P., Miclo, L. and Viens, F. (2003). Precise propagations of chaos estimates for Feynman–Kac and genealogical particle models. Technical Report 03-01, Center for Statistical Decision Sciences and Dept. Statistics, Purdue Univ.
  • Dynkin, E. B. and Mandelbaum, A. (1983). Symmetric statistics, Poisson processes and multiple Wiener integrals. Ann. Statist. 11 739–745.
  • Shorack, G. R. (2000). Probability for Statisticians. Springer, New York.
  • Shiga, T. and Tanaka, H. (1985). Central limit theorem for a system of Markovian particles with mean field interaction. Z. Wahrsch. Verw. Gebiete 69 439–459.