Partenaires

CNRS
Logo tutelle
Logo tutelle
Logo tutelle


Rechercher

Sur ce site

Sur le Web du CNRS


Accueil du site > Séminaires > Probabilités Statistiques et réseaux de neurones > A Metropolis version of the EM algorithm

Vendredi 28 juin 2002 à 9h30

A Metropolis version of the EM algorithm

Carlo Gaetan (Université de Padoue)

Résumé : The Expectation Maximisation (EM) algorithm is a popular technique for maximum likelihood in incomplete data models. In order to overcome its documented limitations,several stochastic variants are proposed in the literature. However, none of these algorithms is guaranteed to provide a global maximizer of the likelihood function. In this talk we briefly review the stochastic variants and we introduce the MEM algorithm --- a Metropolis version of the EM --- that achieves the global maximisation of the likelihood with probability that goes to one when the number of iterations goes to infinity

(This is a joint work with Jian-feng Yao, Université de Rennes).

Dans la même rubrique :