Fundamental limits for learning hidden Markov model parameters - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Fundamental limits for learning hidden Markov model parameters

Kweku Abraham
  • Fonction : Auteur
  • PersonId : 1106463
Elisabeth Gassiat
Zacharie Naulet

Résumé

We study the frontier between learnable and unlearnable hidden Markov models (HMMs). HMMs are flexible tools for clustering dependent data coming from unknown populations. The model parameters are known to be identifiable as soon as the clusters are distinct and the hidden chain is ergodic with a full rank transition matrix. In the limit as any one of these conditions fails, it becomes impossible to identify parameters. For a chain with two hidden states we prove nonasymptotic minimax upper and lower bounds, matching up to constants, which exhibit thresholds at which the parameters become learnable.
Fichier principal
Vignette du fichier
HMM_learning_frontier_arxiv.pdf (381.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03301592 , version 1 (27-07-2021)

Identifiants

  • HAL Id : hal-03301592 , version 1

Citer

Kweku Abraham, Elisabeth Gassiat, Zacharie Naulet. Fundamental limits for learning hidden Markov model parameters. 2021. ⟨hal-03301592⟩

Collections

UNIV-PARIS-SACLAY
5 Consultations
230 Téléchargements

Partager

Gmail Facebook X LinkedIn More