Bounding the expectation of the supremum of an empirical process over a (weak) VC-major class

DOI10.1214/15-EJS1055MaRDI QIDQ309534zbMATH OpenOpenAlexFDO

Authors Yannick Baraud

Publication date 7 September 2016

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1411.5571, https://projecteuclid.org/euclid.ejs/1468849961

zbMATH Keywords

nonparametric estimationconcentration inequalitiesexpectation boundssuprema of empirical processesVC type classes

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Inequalities; stochastic orderings (60E15)

Abstract: Given a bounded class of functions G and independent random variables X1, . . . , Xn, we provide an upper bound for the expectation of the supremum of the empirical process over elements of G having a small variance. Our bound applies in the cases where G is a VC-subgraph or a VC-major class and it is of smaller order than those one could get by using a universal entropy bound over the whole class G . It also involves explicit constants and does not require the knowledge of the entropy of G

Recommendations

• On weakly bounded empirical processes
• Inégalités exponentielles pour les processus empiriques
• Tail bounds for the supremums of empirical processes over unbounded classes of functions
• A local maximal inequality under uniform entropy
• Concentration inequalities and asymptotic results for ratio type empirical processes

Cites work

• A new method for estimation and model selection: \(\rho\)-estimation
• Asymptotic Statistics
• Concentration inequalities and asymptotic results for ratio type empirical processes
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Concentration inequalities. A nonasymptotic theory of independence
• Estimating a regression function
• New concentration inequalities in product spaces
• On the density of families of sets
• Rates of convergence for minimum contrast estimators
• Risk bounds for model selection via penalization
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• The Grenander estimator: A nonasymptotic approach
• Weak convergence and empirical processes. With applications to statistics

Cited in

(15)

• Bounding the expectation of the supremum of empirical processes indexed by Hölder classes
• Robust Bayes-like estimation: rho-Bayes estimation
• Rho-estimators revisited: general theory and applications
• Tests and estimation strategies associated to some loss functions
• Concentration of the empirical level sets of Tukey's halfspace depth
• Robust estimation of a regression function in exponential families
• Robust nonparametric regression based on deep ReLU neural networks
• Tail bounds for the supremums of empirical processes over unbounded classes of functions
• High-dimensional CLT: improvements, non-uniform extensions and large deviations
• A chain rule for the expected suprema of Gaussian processes
• Estimating a density, a hazard rate, and a transition intensity via the \(\rho\)-estimation method
• About the rate function in concentration inequalities for suprema of bounded empirical processes
• Rho-estimators for shape restricted density estimation
• Set structured global empirical risk minimizers are rate optimal in general dimensions
• On weakly bounded empirical processes

This page was built for publication: Bounding the expectation of the supremum of an empirical process over a (weak) VC-major class

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q309534)