Small noise asymptotics of the Bayesian estimator in nonidentifiable models

Marc Joannides 1 François Le Gland 2
2 SIGMA2 - Signal, models, algorithms
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, INRIA Rennes
Abstract : We study the asymptotic behavior of the Bayesian estimator for a deterministic signal in additive Gaussian white noise, in the case where the set of minima of the Kullback-Leibler information is a submanifold of the parameter space. This problem includes as a special case the study of the asymptotic behavior of the nonlinear filter, when the state equation is noise-free, and when the limiting deterministic system is nonobservable. As the noise intensity goes to zero, the posterior probability distribution of the parameter asymptotically concentrates on the submanifold of minima of the Kullback-Leibler information. We give an explicit expression of the limit, and we study the rate of convergence. We apply these results to a practical example where nonidentifiability occurs.
Type de document :
Article dans une revue
Statistical Inference for Stochastic Processes, Springer Verlag, 2002, 5 (1), pp.95-130. 〈10.1023/A:1013737907166〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00912057
Contributeur : Francois Le Gland <>
Soumis le : lundi 2 décembre 2013 - 00:35:23
Dernière modification le : vendredi 16 novembre 2018 - 01:22:31

Lien texte intégral

Identifiants

Collections

Citation

Marc Joannides, François Le Gland. Small noise asymptotics of the Bayesian estimator in nonidentifiable models. Statistical Inference for Stochastic Processes, Springer Verlag, 2002, 5 (1), pp.95-130. 〈10.1023/A:1013737907166〉. 〈hal-00912057〉

Partager

Métriques

Consultations de la notice

205