Discrepancy, chaining and subgaussian processes

DOI10.1214/10-AOP575MaRDI QIDQ533745zbMATH OpenOpenAlexFDO

Authors Shahar Mendelson

Publication date 6 May 2011

Published in The Annals of Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1104.1508

zbMATH Keywords

discrepancysub-Gaussian class of function

Mathematics Subject Classification ID

Gaussian processes (60G15) Geometric probability and stochastic geometry (60D05) Combinatorial probability (60C05)

Abstract: We show that for a typical coordinate projection of a subgaussian class of functions, the infimum over signs $in{f}_{(epsilo{n}_i)}su{p}_{finF}|su{m}_{i=1}^{k}epsilo{n}_{i}f(X_i)|$ is asymptotically smaller than the expectation over signs as a function of the dimension $k$, if the canonical Gaussian process indexed by $F$ is continuous. To that end, we establish a bound on the discrepancy of an arbitrary subset of $mathbb{R}^k$ using properties of the canonical Gaussian process the set indexes, and then obtain quantitative structural information on a typical coordinate projection of a subgaussian class.

Recommendations

• scientific article; zbMATH DE number 4020117
• scientific article; zbMATH DE number 4078394
• On subgaussian random variables
• scientific article; zbMATH DE number 1239570
• scientific article; zbMATH DE number 3888620
• Continuous disintegrations of Gaussian processes
• Discrete and continuous time extremes of Gaussian processes
• Statistical inference for discrete-valued stochastic processes
• \(\varphi\)-sub-Gaussian random processes
• Expectiles for subordinated Gaussian processes with applications

Cites work

• scientific article; zbMATH DE number 4063946 (Why is no real title available?)
• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 3518027 (Why is no real title available?)
• scientific article; zbMATH DE number 1254560 (Why is no real title available?)
• Asymptotic theory of finite dimensional normed spaces. With an appendix by M. Gromov: Isoperimetric inequalities in Riemannian manifolds
• Entropy and the combinatorial dimension
• Gaussian averages of interpolated bodies and applications to approximate reconstruction
• Geometric discrepancy. An illustrated guide
• On the Euclidean Metric Entropy of Convex Bodies
• On the minimum of several random variables
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Regularity of Gaussian processes
• Six Standard Deviations Suffice
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• The Generic Chaining
• The probabilistic method. With an appendix on the life and work of Paul Erdős.
• Tight upper bounds for the discrepancy of half-spaces
• Uniform Central Limit Theorems
• Weak convergence and empirical processes. With applications to statistics

Cited in

(4)

• On the reversed sub-martingale property of empirical discrepancies in arbitrary sample spaces
• On the compression phenomenon of typical discrepancies
• Orthogonal statistical learning
• Dvoretzky type theorems for subgaussian coordinate projections

This page was built for publication: Discrepancy, chaining and subgaussian processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q533745)