Donsker classes of sets

DOI10.1007/BF00322017MaRDI QIDQ1093240zbMATH OpenFDO

Authors Michel Talagrand

Publication date 1988

Published in Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/BF00322017

zbMATH Keywords

central limit theoremempirical processeslaw of large numberslocal theory of Banach spacesrate of convergence

Mathematics Subject Classification ID

Measures and integrals in product spaces (28A35) Central limit and other weak theorems (60F05) Strong limit theorems (60F15)

Review text

We study the central limit theorem (CLT) and the law of large numbers (LLN) for empirical processes indexed by a (countable) class of sets \({\mathcal C}\). The main result, of purely measure-theoretical nature, relates different ways to measure the ``size of \({\mathcal C}\). It relies on a new rearrangement inequality that has been inspired by techniques used in the local theory of Banach spaces. As an application, we give sharp necessary conditions for the CLT, that are in some sense the best possible. We also obtain a way to compute the rate of convergence in the LLN.

Recommendations

• scientific article; zbMATH DE number 3919457
• Classes de Donsker et fonctions d'entropie relatives aux mesures aléatoires. (Donsker classes and entropy function for random measures)
• Donsker classes and random geometry
• New Donsker classes
• scientific article; zbMATH DE number 4107816

Cites work

• Donsker classes and random geometry
• Embedding of \(\ell^ k_{\infty}\) in finite dimensional Banach spaces
• Empirical discrepancies and subadditive processes
• Measurability problems for empirical processes
• On the density of families of sets
• Pettis integral and measure theory
• Regularity of Gaussian processes
• Some limit theorems for empirical processes (with discussion)
• The central limit theorem for stochastic processes. II
• The dimension of almost spherical sections of convex bodies
• The Glivenko-Cantelli problem

Cited in

(14)

• Gaussian approximation of the empirical process under random entropy conditions
• Donsker classes and random geometry
• Gelfand numbers of operators with values in a Hilbert space
• Komlós-Major-Tusnády approximation for the general empirical process and Haar expansions of classes of functions
• Vapnik-Chervonenkis dimension and (pseudo-)hyperplane arrangements
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• A note on limit theorems for perturbed empirical processes
• A CLT for empirical processes involving time-dependent data
• Selector processes on classes of sets
• scientific article; zbMATH DE number 3919457 (Why is no real title available?)
• VC bounds on the cardinality of nearly orthogonal function classes
• Ergodic Regularity of Some Donsker Classes
• Classes de Donsker et fonctions d'entropie relatives aux mesures aléatoires. (Donsker classes and entropy function for random measures)
• The Glivenko-Cantelli problem, ten years later

This page was built for publication: Donsker classes of sets

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1093240)