MINIMAX ADAPTIVE ESTIMATION OF NONPARAMETRIC HIDDEN MARKOV MODELS - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2015

MINIMAX ADAPTIVE ESTIMATION OF NONPARAMETRIC HIDDEN MARKOV MODELS

Résumé

We consider stationary hidden Markov models with finite state space and nonparametric modeling of the emission distributions. It has remained unknown until very recently that such models are identifiable. In this paper, we propose a new penalized least-squares estimator for the emission distributions which is statistically optimal and practically tractable. We prove a non asymptotic oracle inequality for our nonparametric estimator of the emission distributions. A consequence is that this new estimator is rate minimax adaptive up to a logarithmic term. Our methodology is based on projections of the emission distributions onto nested subspaces of increasing complexity. The popular spectral estimators are unable to achieve the optimal rate but may be used as initial points in our procedure. Simulations are given that show the improvement obtained when applying the least-squares minimization consecutively to the spectral estimation.
Fichier principal
Vignette du fichier
NPHMM-C2-YCE.pdf (412.84 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01105424 , version 1 (20-01-2015)
hal-01105424 , version 2 (24-07-2015)
hal-01105424 , version 3 (27-12-2015)

Identifiants

Citer

Yohann de Castro, Élisabeth Gassiat, Claire Lacour. MINIMAX ADAPTIVE ESTIMATION OF NONPARAMETRIC HIDDEN MARKOV MODELS. 2015. ⟨hal-01105424v2⟩
329 Consultations
199 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More