Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: $L^p$ and almost sure rates of convergence - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Multivariate Analysis Année : 2016

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

(1)
1

Résumé

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.

Dates et versions

hal-01413440 , version 1 (09-12-2016)

Identifiants

Citer

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, 2016, 146, pp.209 - 222. ⟨10.1016/j.jmva.2015.09.013⟩. ⟨hal-01413440⟩
86 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More