Online estimation of the geometric median in Hilbert spaces : non asymptotic confidence balls

Abstract

Estimation procedures based on recursive algorithms are interesting and powerful techniques that are able to deal rapidly with (very) large samples of high dimensional data. The collected data may be contaminated by noise so that robust location indicators, such as the geometric median, may be preferred to the mean. In this context, an estimator of the geometric median based on a fast and efficient averaged non linear stochastic gradient algorithm has been developed by Cardot, Cénac and Zitt (2013). This work aims at studying more precisely the non asymptotic behavior of this algorithm by giving non asymptotic confidence balls. This new result is based on the derivation of improved $L^2$ rates of convergence as well as an exponential inequality for the martingale terms of the recursive non linear Robbins-Monro algorithm.

References in corpus (2)

• Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm
• Robust functional principal components: A projection-pursuit approach

Cited by in corpus (4)

• Optimal non-asymptotic bound of the Ruppert-Polyak averaging without strong convexity
• Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: $L^p$ and almost sure rates of convergence
• Asymptotic study of stochastic adaptive algorithm in non-convex landscape
• Robust Extrinsic Regression Analysis for Manifold Valued Data