Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: L-p and almost sure rates of convergence

Abstract : The geometric median, also called L-1-median, is often used in robust statistics. Moreover, it is more and more usual to deal with large samples taking values in high dimensional spaces. In this context, a fast recursive estimator has been introduced by Cardot et al. (2013). This work aims at studying more precisely the asymptotic behavior of the estimators of the geometric median based on such non linear stochastic gradient algorithms. The L-p rates of convergence as well as almost sure rates of convergence of these estimators are derived in general separable Hilbert spaces. Moreover, the optimal rates of convergence in quadratic mean of the averaged algorithm are also given. (C) 2015 Elsevier Inc. All rights reserved.
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01413440
Contributeur : Imb - Université de Bourgogne <>
Soumis le : vendredi 9 décembre 2016 - 17:35:54
Dernière modification le : mardi 13 décembre 2016 - 09:30:19

Identifiants

Collections

Citation

Antoine Godichon-Baggioni. Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: L-p and almost sure rates of convergence. Journal of Multivariate Analysis, Elsevier, 2016, 146, pp.209 - 222. <http://www.sciencedirect.com/science/article/pii/S0047259X15002274>. <10.1016/j.jmva.2015.09.013>. <hal-01413440>

Partager

Métriques

Consultations de la notice

27