Stochastic algorithms for computing means of probability measures - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Stochastic Processes and their Applications Année : 2012

Stochastic algorithms for computing means of probability measures

Résumé

Consider a probability measure supported by a regular geodesic ball in a manifold. For any p larger than or equal to 1 we define a stochastic algorithm which converges almost surely to the p-mean of the measure. Assuming furthermore that the functional to minimize is regular around the p-mean, we prove that a natural renormalization of the inhomogeneous Markov chain converges in law into an inhomogeneous diffusion process. We give an explicit expression of this process, as well as its local characteristic.
Fichier principal
Vignette du fichier
algo_means_rev.pdf (202.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00540623 , version 1 (28-11-2010)
hal-00540623 , version 2 (24-06-2011)

Identifiants

Citer

Marc Arnaudon, Clément Dombry, Anthony Phan, Le Yang. Stochastic algorithms for computing means of probability measures. Stochastic Processes and their Applications, 2012, 122, pp.1437-1455. ⟨10.1016/j.spa.2011.12.011⟩. ⟨hal-00540623v2⟩

Collections

CNRS UNIV-POITIERS
177 Consultations
181 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More