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

DOI10.1214/16-AOS1460zbMATH Open1371.62027arXiv1501.06930OpenAlexW4301224720MaRDI QIDQ2012199FDOQ2012199

Peggy Cénac, Antoine Godichon-Baggioni, Hervé Cardot

Publication date: 28 July 2017

Published in: The Annals of Statistics (Search for Journal in Brave)

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, C'enac 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.

Full work available at URL: https://arxiv.org/abs/1501.06930

zbMATH Keywords

functional data analysisrecursive estimationrobust statisticsspatial medianstochastic gradient algorithmsmartingales in Hilbert spaces

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric robustness (62G35) Nonparametric tolerance and confidence regions (62G15) Stochastic approximation (62L20)

Cited In (24)

• Conditional quantile sequential estimation for stochastic codes
• Affine-equivariant inference for multivariate location under \({L_p}\) loss functions
• Optimal non-asymptotic analysis of the Ruppert-Polyak averaging stochastic algorithm
• Volatility estimation in a nonlinear heteroscedastic functional regression model with martingale difference errors
• On the rates of convergence of parallelized averaged stochastic gradient algorithms
• Algorithms of robust stochastic optimization based on mirror descent method
• The geometric median and applications to robust mean estimation
• Non asymptotic controls on a recursive superquantile approximation
• Halfspace depths for scatter, concentration and shape matrices
• L^p and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective
• Convergence in quadratic mean of averaged stochastic gradient algorithms without strong convexity nor bounded gradient
• Evaluating the complexity of some families of functional data
• Asymptotic properties of high-dimensional spatial median in elliptical distributions with application
• Online bootstrap inference for the geometric median
• Stochastic approximation algorithms for superquantiles estimation
• An efficient averaged stochastic Gauss-Newton algorithm for estimating parameters of nonlinear regressions models
• On the Behavior of Extreme d-dimensional Spatial Quantiles Under Minimal Assumptions
• Online estimation of the asymptotic variance for averaged stochastic gradient algorithms
• Spatial quantiles on the hypersphere
• Fast estimation of the median covariation matrix with application to online robust principal components analysis
• Multivariate \(\rho \)-quantiles: a spatial approach
• Title not available (Why is that?)
• Online stochastic Newton methods for estimating the geometric median and applications
• On weighted multivariate sign functions

This page was built for publication: Online estimation of the geometric median in Hilbert spaces: nonasymptotic confidence balls

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2012199)