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

DOI10.1016/j.jmva.2015.09.013zbMath1337.62053arXiv1504.02267OpenAlexW1833328064MaRDI QIDQ268758

Antoine Godichon-Baggioni

Publication date: 15 April 2016

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1504.02267

zbMATH Keywords

law of large numbersrobust statisticsfunctional data analysisrecursive estimationmartingales in Hilbert spacespatial medianstochastic gradient algorithms

Mathematics Subject Classification ID

Nonparametric robustness (62G35) Nonparametric estimation (62G05) Stochastic approximation (62L20) (L^p)-limit theorems (60F25)

Related Items (15)

L^p and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective ⋮ An introduction to recent advances in high/infinite dimensional statistics ⋮ Online estimation of hazard rate under random censoring ⋮ Inversion-free subsampling Newton's method for large sample logistic regression ⋮ Optimal non-asymptotic analysis of the Ruppert-Polyak averaging stochastic algorithm ⋮ On the rates of convergence of parallelized averaged stochastic gradient algorithms ⋮ Convergence in quadratic mean of averaged stochastic gradient algorithms without strong convexity nor bounded gradient ⋮ Online estimation of integrated squared density derivatives ⋮ Non asymptotic controls on a recursive superquantile approximation ⋮ A compact law of the iterated logarithm for online estimator of hazard rate under random censoring ⋮ Fast estimation of the median covariation matrix with application to online robust principal components analysis ⋮ Recursive estimators of integrated squared density derivatives ⋮ Stochastic approximation algorithms for superquantiles estimation ⋮ Online estimation of the asymptotic variance for averaged stochastic gradient algorithms ⋮ Conditional quantile sequential estimation for stochastic codes

Uses Software

• fda (R)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm
• A partial overview of the theory of statistics with functional data
• Stochastic algorithms for computing means of probability measures
• A fast and recursive algorithm for clustering large datasets with \(k\)-medians
• Robust functional principal components: a projection-pursuit approach
• Multivariate location estimation using extension of \(R\)-estimates through \(U\)-statistics type approach
• Weiszfeld's method: old and new results
• Functional data analysis.
• Nonparametric functional data analysis. Theory and practice.
• The spatial distribution in infinite dimensional spaces and related quantiles and depths
• Riemannian median and its estimation
• Robust functional estimation using the median and spherical principal components
• Acceleration of Stochastic Approximation by Averaging
• The multivariate L ₁ -median and associated data depth
• Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms
• Convergent estimators for the l₁-median of banach valued random variable
• A note on Fermat's problem
• Note on the median of a multivariate distribution
• A Stochastic Approximation Method

This page was built for publication: Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: \(L^p\) and almost sure rates of convergence