Abstract
The approximation of the Feynman-Kac semigroups by systems of interacting particles is a very active research field, with applications in many different areas. In this paper, we study the parallelization of such approximations. The total population of particles is divided into sub-populations, referred to as islands. The particles within each island follow the usual selection/mutation dynamics. We show that the evolution of each island is also driven by a Feynman-Kac semigroup, whose transition and potential can be explicitly related to ones of the original problem. Therefore, the same genetic type approximation of the Feynman-Kac semi-group may be used at the island level; each island might undergo selection/mutation algorithm. We investigate the impact of the population size within each island and the number of islands, and study different type of interactions. We find conditions under which introducing interactions between islands is beneficial. The theoretical results are supported by some Monte Carlo experiments.
Similar content being viewed by others
Notes
A Markov kernel on \(\mathbb{E}_{n} \times\mathcal{E}_{n+1}\) is a function \(M_{n+1}:\mathbb{E}_{n} \times\mathcal{E}_{n+1} \rightarrow[0;1]\), such that, for all \(x_{n} \in \mathbb{E}_{n}\), A n+1↦M n+1(x n ,A n+1) is a probability measure on \((\mathbb{E}_{n+1},\mathcal{E}_{n+1})\) and for any \(A_{n+1} \in \mathcal{E}_{n+1}\), x n ↦M n+1(x n ,A n+1) is a measurable function.
References
Arnaud, E., Le Gland, F.: SMC with Adaptive Resampling: Large Sample Asymptotics, pp. 481–484 (2009)
Cappé, O., Moulines, E.: On the use of particle filtering for maximum likelihood parameter estimation. In: European Signal Processing Conference (EUSIPCO), Antalya, Turkey (2005)
Casarin, R., Grassi, S., Ravazzolo, F., Van Dijk, H.K.: Parallel sequential Monte Carlo for efficient density combination: the deco Matlab toolboox. Tinbergen Institute Discussion Paper, 055/III (2013)
Chopin, N.: A sequential particle filter method for static models. Biometrika 89, 539–552 (2002)
Chopin, N., Jacob, P., Papaspiliopoulos, O.: SMC2: a sequential Monte Carlo algorithm with particle Markov chain Monte Carlo updates. J. R. Stat. Soc. B. 75(3), 397–426 (2013). doi:10.1111/j.1467-9868.2012.01046.x
Del Moral, P.: Feynman-Kac Formulae. Genealogical and Interacting Particle Systems with Applications. Springer, Berlin (2004)
Del Moral, P., Doucet, A., Jasra, A.: On adaptive resampling strategies for sequential Monte Carlo methods. Bernoulli 18(1), 252–278 (2012a)
Del Moral, P., Hu, P., Wu, L.: On the concentration properties of interacting particle processes. Found. Trends Mach. Learn. 3(3–4), 225–289 (2012b)
Douc, R., Moulines, E.: Limit theorems for weighted samples with applications to sequential Monte Carlo methods. Ann. Stat. 36(5), 2344–2376 (2008)
Doucet, A., Freitas, N.D. (eds.): Sequential Monte Carlo Methods in Practice. Springer, New York (2001)
Durham, G., Geweke, J.: Massively parallel sequential Monte Carlo for Bayesian inference. Manuscript, URL http://www.censoc.uts.edu.au/pdfs/geweke_papers/gp_working_9.pdf (2011)
Jasra, A., Doucet, A., Stephens, D.A., Holmes, C.C.: Interacting sequential Monte Carlo samplers for trans-dimensional simulation. Comput. Stat. Data Anal. 52, 1765–1791 (2008)
Liu, J.S.: Monte Carlo Strategies in Scientific Computing. Springer, New York (2001)
Liu, J., Chen, R.: Blind deconvolution via sequential imputations. J. Am. Stat. Assoc. 90(420), 567–576 (1995)
Acknowledgements
This work is supported by the Agence Nationale de la Recherche through the 2009-2012 project Big MC. The work of Christelle Vergé is financially supported by CNES (Centre National d’Etudes Spatiales) and Onera, The French Aerospace Lab.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Vergé, C., Dubarry, C., Del Moral, P. et al. On parallel implementation of sequential Monte Carlo methods: the island particle model. Stat Comput 25, 243–260 (2015). https://doi.org/10.1007/s11222-013-9429-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-013-9429-x