Central Limit Theorems for Stochastic Approximation with controlled Markov chain dynamics - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2013

Central Limit Theorems for Stochastic Approximation with controlled Markov chain dynamics

Résumé

This paper provides a Central Limit Theorem (CLT) for a process $\{\theta_n, n\geq 0\}$ satisfying a stochastic approximation (SA) equation of the form $\theta_{n+1} = \theta_n + \gamma_{n+1} H(\theta_n,X_{n+1})$; a CLT for the associated average sequence is also established. The originality of this paper is to address the case of controlled Markov chain dynamics $\{X_n, n\geq 0 \}$ and the case of multiple targets. The framework also accomodates (randomly) truncated SA algorithms. Sufficient conditions for CLT's to hold are provided as well as comments on how these conditions extend previous works (such as independent and identically distributed dynamics, the Robbins-Monro dynamic or the single target case). The paper gives a special emphasis on how these conditions hold for SA with controlled Markov chain dynamics and multiple targets; it is proved that this paper improves on existing works.
Fichier principal
Vignette du fichier
CLT_arXiv.pdf (273.48 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00861097 , version 1 (11-09-2013)

Identifiants

Citer

Gersende Fort. Central Limit Theorems for Stochastic Approximation with controlled Markov chain dynamics. 2013. ⟨hal-00861097⟩
180 Consultations
416 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More