Monte Carlo methods in nonlinear filtering and importance sampling

François Le Gland 1
1 MEFISTO
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : For the calculation of conditional expectations in nonlinear filtering of Markov processes, one may think to use Monte Carlo techniques, as an alternative to the numerical solution of Zakai equation (a stochastic PDE). We show that a direct implementation of this idea is unefficient, and we propose a modified algorithm, that uses importance sampling, where our choice of the new probability is based on large deviations arguments.
Type de document :
Communication dans un congrès
Proceedings of the 23rd IEEE Conference on Decision and Control, Las Vegas 1984, Dec 1984, Las Vegas, United States. pp.31-32, 1984, 〈10.1109/CDC.1984.272246〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00912071
Contributeur : Francois Le Gland <>
Soumis le : dimanche 1 décembre 2013 - 23:30:54
Dernière modification le : samedi 27 janvier 2018 - 01:30:50

Identifiants

Collections

Citation

François Le Gland. Monte Carlo methods in nonlinear filtering and importance sampling. Proceedings of the 23rd IEEE Conference on Decision and Control, Las Vegas 1984, Dec 1984, Las Vegas, United States. pp.31-32, 1984, 〈10.1109/CDC.1984.272246〉. 〈hal-00912071〉

Partager

Métriques

Consultations de la notice

127