A Functional Central Limit Theorem for a Class of Interacting Markov Chain Monte Carlo Methods

Bernard Bercu (Université de Bordeaux)
Pierre Del Moral (INRIA et Université de Bordeaux)
Arnaud Doucet (University of British Columbia)

Abstract


We present a functional central limit theorem for a new class of interacting Markov chain Monte Carlo algorithms. These stochastic algorithms have been recently introduced to solve non-linear measure-valued equations. We provide an original theoretical analysis based on semigroup techniques on distribution spaces and fluctuation theorems for self-interacting random fields. Additionally we also present a series of sharp mean error bounds in terms of the semigroup associated with the first order expansion of the limiting measure-valued process. We illustrate our results in the context of Feynman-Kac semigroups

Full Text: Download PDF | View PDF online (requires PDF plugin)

Pages: 2130-2155

Publication Date: October 4, 2009

DOI: 10.1214/EJP.v14-701

References

  1. A. Brockwell, P. Del Moral, and A. Doucet. Sequentially interacting Markov chain Monte Carlo. Technical report, Department of Statistics, University of British Columbia (2007). }
  2. P. Del Moral, Feynman-Kac formulae. Genealogical and interacting particle systems, with applications, Springer Verlag New York, Series: Probability and its Applications (2004). MR2044973
  3. P. Del Moral, and A. Doucet. Interacting Markov Chain Monte Carlo Methods For Solving Nonlinear Measure-Valued Equations. MR2220075 (2007g:60116)
  4. Del Moral, Pierre; Miclo, Laurent. On convergence of chains with occupational self-interactions.Stochastic analysis with applications to mathematical finance. Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 460 (2004), no. 2041, 325--346. MR2052266 (2005m:60154)
  5. Sequential Monte Carlo methods in practice.Edited by Arnaud Doucet, Nando de Freitas and Neil Gordon.Statistics for Engineering and Information Science. Springer-Verlag, New York, 2001. xxviii+581 pp. ISBN: 0-387-95146-6 MR1847783 (2003h:65007)
  6. Haagerup. U. The best constants in the Khintchine inequality. Studia Math., vol. 70, pp. 231--283 (1982). MR0654838
  7. Jacod. J and ShiryaevA.N. Limit Theorems for Stochastic Processes, A Series of Comprehensive Studies in Mathematics 288, Springer-Verlag (1987).
  8. Andrieu, Christophe; Jasra, Ajay; Doucet, Arnaud; Del Moral, Pierre. Non-linear Markov chain Monte Carlo. Conference Oxford sur les méthodes de Monte Carlo séquentielles, 79--84, ESAIM Proc., 19, EDP Sci., Les Ulis, 2007. MR2405652 (2009g:60047)
  9. Andrieu, Christophe; Jasra, Ajay; Doucet, Arnaud; Del Moral, Pierre. A note on convergence of the equi-energy sampler. Stoch. Anal. Appl. 26 (2008), no. 2, 298--312. MR2399737 (2009d:82144)
  10. Shiryaev, A. N. Probability.Translated from the first (1980) Russian edition by R. P. Boas.Second edition.Graduate Texts in Mathematics, 95. Springer-Verlag, New York, 1996. xvi+623 pp. ISBN: 0-387-94549-0 MR1368405 (97c:60003)


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.