Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm

DOI10.3150/11-BEJ390zbMath1259.62068arXiv1101.4316MaRDI QIDQ89452

Hervé Cardot, Pierre-André Zitt, Peggy Cénac, Pierre-André Zitt, Peggy Cénac

Publication date: 1 February 2013

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1101.4316

zbMATH Keywords

online algorithmsrecursive estimationfunctional datahigh dimensionsspatial medianCLTRobbins-Monro algorithm\(L^{1}\)-mediangeometric quantiles

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Asymptotic distribution theory in statistics (62E20) Sequential estimation (62L12) Probability theory on linear topological spaces (60B11)

Related Items (36)

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 ⋮ Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: \(L^p\) and almost sure rates of convergence ⋮ Robust Bregman clustering ⋮ Robust functional principal components for sparse longitudinal data ⋮ Multivariate \(\rho \)-quantiles: a spatial approach ⋮ Choices and intervals ⋮ Depth-based nonparametric description of functional data, with emphasis on use of spatial depth ⋮ Improved similarity-based modeling for the classification of rotating-machine failures ⋮ A stochastic algorithm finding generalized means on compact manifolds ⋮ Robust optimal estimation of location from discretely sampled functional data ⋮ Optimal non-asymptotic analysis of the Ruppert-Polyak averaging stochastic algorithm ⋮ Extreme geometric quantiles in a multivariate regular variation framework ⋮ 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 ⋮ Spatial quantiles on the hypersphere ⋮ Functional spherical autocorrelation: a robust estimate of the autocorrelation of a functional time series ⋮ A \(k\)-points-based distance for robust geometric inference ⋮ Recursive estimation of the conditional geometric median in Hilbert spaces ⋮ The deepest point for distributions in infinite dimensional spaces ⋮ The spatial sign covariance operator: asymptotic results and applications ⋮ Non asymptotic controls on a recursive superquantile approximation ⋮ Robust functional sliced inverse regression ⋮ Fast estimation of the median covariation matrix with application to online robust principal components analysis ⋮ Kmedians ⋮ Robust simultaneous inference for the mean function of functional data ⋮ Geometric median and robust estimation in Banach spaces ⋮ The spatial distribution in infinite dimensional spaces and related quantiles and depths ⋮ Convergence of Markovian Stochastic Approximation with Discontinuous Dynamics ⋮ Stochastic approximation algorithms for superquantiles estimation ⋮ Online estimation of the asymptotic variance for averaged stochastic gradient algorithms ⋮ Robust and Scalable Bayes via a Median of Subset Posterior Measures ⋮ Multi-sample comparison using spatial signs for infinite dimensional data ⋮ Spatial depth-based classification for functional data ⋮ Affine-equivariant inference for multivariate location under \({L_p}\) loss functions ⋮ On the Behavior of Extreme d-dimensional Spatial Quantiles Under Minimal Assumptions

Uses Software

• AS 78
• Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic algorithms for computing means of probability measures
• A fast and recursive algorithm for clustering large datasets with \(k\)-medians
• Exact \(L_{2}\)-small ball asymptotics of Gaussian processes and the spectrum of boundary-value problems
• Concavity and estimation
• Robust estimation and classification for functional data via projection-based depth notions
• A Newton-Raphson version of the multivariate Robbins-Monro procedure
• Multivariate location estimation using extension of \(R\)-estimates through \(U\)-statistics type approach
• Stochastic approximation methods for constrained and unconstrained systems
• \(M\)-estimation, convexity and quantiles
• Trimmed means for functional data
• The averaged Robbins-Monro method for linear problems in a Banach space
• Design-based estimation for geometric quantiles with application to outlier detection
• Online learning algorithms
• On a Geometric Notion of Quantiles for Multivariate Data
• Robust functional estimation using the median and spherical principal components
• Acceleration of Stochastic Approximation by Averaging
• An invariance principle for the Robbins-Monro process in a Hilbert space
• 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
• Note on the median of a multivariate distribution
• Robust Statistics

This page was built for publication: Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm