Large ball probabilities, Gaussian comparison and anti-concentration

DOI10.3150/18-BEJ1062zbMath1428.62187arXiv1708.08663OpenAlexW2972455288MaRDI QIDQ2325333

Vladimir V. Ulyanov, Vladimir Spokoiny, Alexey Naumov, Friedrich Götze

Publication date: 25 September 2019

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1708.08663

zbMATH Keywords

high-dimensional inferenceSchatten normdimension free boundsGaussian anti-concentration inequalitiesGaussian comparisonhigh-dimensional CLT

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Central limit and other weak theorems (60F05) Probability theory on linear topological spaces (60B11)

Related Items

Chebyshev--Hermite Polynomials and Distributions of Polynomials in Gaussian Random Variables, Inference via randomized test statistics, On Alternative Approximating Distributions in the Multivariate Version of Kolmogorov's Second Uniform Limit Theorem, Gaussian approximation for penalized Wasserstein barycenters, Dimension Free Nonasymptotic Bounds on the Accuracy of High-Dimensional Laplace Approximation, Stein's method, smoothing and functional approximation, Stein's method, Gaussian processes and palm measures, with applications to queueing, Nonasymptotic estimates for the closeness of Gaussian measures on balls, Confidence sets for spectral projectors of covariance matrices, Bootstrap confidence sets for spectral projectors of sample covariance, Distributions of polynomials in Gaussian random variables under constraints on the powers of variables, Distributions of second order polynomials in Gaussian random variables

Cites Work

• Finite sample Bernstein-von Mises theorem for semiparametric problems
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• Berry-Esseen bounds in the entropic central limit theorem
• Penalized maximum likelihood estimation and effective dimension
• Probability in Banach spaces. Isoperimetry and processes
• Bernstein-von Mises theorems for Gaussian regression with increasing number of regressors
• A semiparametric Bernstein-von Mises theorem for Gaussian process priors
• User-friendly tail bounds for sums of random matrices
• New applications of Arak's inequalities to the Littlewood-Offord problem
• Bootstrap confidence sets under model misspecification
• Normal approximation - some recent advances
• The reverse isoperimetric problem for Gaussian measure
• Nonasymptotic estimates for the closeness of Gaussian measures on balls
• Confidence sets for spectral projectors of covariance matrices
• On the dependence of the Berry-Esseen bound on dimension
• Sums and Gaussian vectors
• On coverage and local radial rates of credible sets
• Bounds on the maximum of the density for sums of independent random variables
• The Littlewood-Offord problem and invertibility of random matrices
• Some Approximation Problems in Statistics and Probability
• Asymptotic Expansions for Distributions of Sums of Independent Random Variables inH
• Lectures on Gaussian Processes
• THE EIGEN- AND SINGULAR VALUES OF THE SUM AND PRODUCT OF LINEAR OPERATORS
• A Lyapunov-type Bound in R^d
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item