Nonasymptotic control of the MLE for misspecified nonparametric hidden Markov models - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Nonasymptotic control of the MLE for misspecified nonparametric hidden Markov models

Contrôle non-asymptotique de l'EMV pour les modèles de Markov cachés mal spécifiés

Luc Lehéricy

Résumé

Finite state space hidden Markov models are flexible tools to model phenomena with complex time dependencies: any process distribution can be approximated by a hidden Markov model with enough hidden states. We consider the problem of estimating an unknown process distribution using nonparametric hidden Markov models in the misspecified setting, that is when the data-generating process may not be a hidden Markov model. We show that when the true distribution is exponentially mixing and satisfies a forgetting assumption, the maximum likelihood estimator recovers the best approximation of the true distribution. We prove a finite sample bound on the resulting error and show that it is optimal in the minimax sense--up to logarithmic factors--when the model is well specified.
Fichier principal
Vignette du fichier
MLE_misspeNPHMM_HAL.pdf (460.67 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01833274 , version 1 (09-07-2018)
hal-01833274 , version 2 (12-02-2021)

Licence

Paternité - Partage selon les Conditions Initiales

Identifiants

Citer

Luc Lehéricy. Nonasymptotic control of the MLE for misspecified nonparametric hidden Markov models. 2018. ⟨hal-01833274v2⟩
82 Consultations
75 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More