Skip to Main content Skip to Navigation
Conference papers

Exponential forgetting and geometric ergodicity in HMM's

François Le Gland 1 Laurent Mevel 1 
1 SIGMA2 - Signal, models, algorithms
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, INRIA Rennes
Abstract : We consider a hidden Markov model with multidimensional observations and with misspecification, i.e. the assumed coefficients (transition probability matrix and observation conditional densities) are possibly different from the true coefficients. Under mild assumptions on the coefficients of both the true and the assumed models, we prove that: 1) the prediction filter forgets almost surely their initial condition exponentially fast; and 2) the extended Markov chain, whose components are the unobserved Markov chain, the observation sequence and the prediction filter, is geometrically ergodic, and has a unique invariant probability distribution.
Document type :
Conference papers
Complete list of metadata
Contributor : Francois Le Gland Connect in order to contact the contributor
Submitted on : Friday, December 20, 2013 - 5:52:11 PM
Last modification on : Friday, February 4, 2022 - 3:20:06 AM



François Le Gland, Laurent Mevel. Exponential forgetting and geometric ergodicity in HMM's. Proceedings of the 36th Conference on Decision and Control, San Diego 1997, IEEE--CSS, Dec 1997, San Diego, United States. pp.537-542, ⟨10.1109/CDC.1997.650683⟩. ⟨hal-00912076⟩



Record views