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 (53)

• Sparsity and Incoherence in Compressive Sampling
• Global uniform risk bounds for wavelet deconvolution estimators
• Gaussian and bootstrap approximations for high-dimensional U-statistics and their applications
• Moving Beyond Sub-Gaussianity in High-Dimensional Statistics: Applications in Covariance Estimation and Linear Regression
• Exact Matrix Completion via Convex Optimization
• Nonparametric adaptive estimation for pure jump Lévy processes
• Adaptive functional linear regression
• Estimation for Lévy processes from high frequency data within a long time interval
• A Permutation-based Model for Crowd Labeling: Optimal Estimation and Robustness
• A new method for estimation and model selection: $\rho$-estimation
• Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections
• A Simple Adjustment for Bandwidth Snooping
• New concentration inequalities for suprema of empirical processes
• Adaptive estimation of the transition density of a particular hidden Markov chain
• Concentration inequalities for bounded functionals via generalized log-Sobolev inequalities
• Empirical risk minimization is optimal for the convex aggregation problem
• Bandwidth Selection for the Wolverton-Wagner Estimator
• On a Nadaraya-Watson Estimator with Two Bandwidths
• Functional Response Designs via the Analytic Permutation Test
• Exponential Concentration Inequalities for Additive Functionals of Markov Chains
• The multiplicative coalescent, inhomogeneous continuum random trees, and new universality classes for critical random graphs
• Localized Complexities for Transductive Learning
• Statistical analysis of Wasserstein GANs with applications to time series forecasting
• Optimal model selection for density estimation of stationary data under various mixing conditions
• Adaptive pointwise estimation of conditional density function
• Least squares type estimation of the transition density of a particular hidden Markov chain
• Breaking the $1/\sqrt{n}$ Barrier: Faster Rates for Permutation-based Models in Polynomial Time
• A probabilistic approach to the leader problem in random graphs
• Stability results for random sampling of sparse trigonometric polynomials
• A Bernstein-type inequality for suprema of random processes with an application to statistics
• On the Bennett-Hoeffding inequality
• Gaussian approximation for the sup-norm of high-dimensional matrix-variate U-statistics and its applications
• On the concentration properties of Interacting particle processes
• Excess Risk Bounds for Exponentially Concave Losses
• Adaptive non-parametric estimation in the presence of dependence
• Nonparametric Estimation of the Transition Density Function for Diffusion Processes
• Minimal penalty for Goldenshluger-Lepski method
• Multiplicative deconvolution estimator based on a ridge approach
• A concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noise
• Concentration inequalities using higher moments information
• A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models
• Optimal model selection in density estimation
• Data-driven aggregation in non-parametric density estimation on the real line
• Multiplicative deconvolution under unknown error distribution
• Gaussian martingale inequality applies to random functions and maxima of empirical processes
• Stochastic Lipschitz continuity for high dimensional Lasso with multiple linear covariate structures or hidden linear covariates
• Partially adaptive nonparametric instrumental regression
• Characterization of LIL behavior in Banach space
• A Tight Bound of Tail Probabilities for a Discrete-time Martingale with Uniformly Bounded Jumps
• Data-driven aggregation in circular deconvolution
• A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
• A few remarks on the operator norm of random Toeplitz matrices
• Nonparametric adaptive inference of birth and death models in a large population limit