Concentration around the mean for maxima of empirical processes

Abstract

In this paper we give optimal constants in Talagrand's concentration inequalities for maxima of empirical processes associated to independent and eventually nonidentically distributed random variables. Our approach is based on the entropy method introduced by Ledoux.

Published at http://dx.doi.org/10.1214/009117905000000044 in the Annals of Probability (http://www.imstat.org/aop/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (22)

• Sparsity and Incoherence in Compressive Sampling
• Global uniform risk bounds for wavelet deconvolution estimators
• Exact Matrix Completion via Convex Optimization
• Estimation for Lévy processes from high frequency data within a long time interval
• Adaptive estimation of the transition density of a particular hidden Markov chain
• Localized Complexities for Transductive Learning
• Statistical analysis of Wasserstein GANs with applications to time series forecasting
• Least squares type estimation of the transition density of a particular hidden Markov chain
• A Bernstein-type inequality for suprema of random processes with an application to statistics
• A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models
• Multiplicative deconvolution estimator based on a ridge approach
• Nonparametric Estimation of the Transition Density Function for Diffusion Processes
• Data-driven aggregation in non-parametric density estimation on the real line
• Multiplicative deconvolution under unknown error distribution
• Stochastic Lipschitz continuity for high dimensional Lasso with multiple linear covariate structures or hidden linear covariates
• Gaussian martingale inequality applies to random functions and maxima of empirical processes
• A few remarks on the operator norm of random Toeplitz matrices
• A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
• Characterization of LIL behavior in Banach space
• A Tight Bound of Tail Probabilities for a Discrete-time Martingale with Uniformly Bounded Jumps
• Nonparametric adaptive inference of birth and death models in a large population limit
• Data-driven aggregation in circular deconvolution