High-dimensional CLT: improvements, non-uniform extensions and large deviations

DOI10.3150/20-BEJ1233zbMath1475.60054arXiv1806.06153OpenAlexW3108539010MaRDI QIDQ2214242

Debapratim Banerjee, Arun Kumar Kuchibhotla, Somabha Mukherjee

Publication date: 7 December 2020

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.06153

zbMATH Keywords

empirical processesanti-concentrationOrlicz normspost-selection inferenceCramér-type large deviationnonuniform CLT

Mathematics Subject Classification ID

Gaussian processes (60G15) Probability measures on topological spaces (60B05) Central limit and other weak theorems (60F05) Large deviations (60F10)

Related Items (7)

Notes on the dimension dependence in high-dimensional central limit theorems for hyperrectangles ⋮ Testing the martingale difference hypothesis in high dimension ⋮ UNIFORM-IN-SUBMODEL BOUNDS FOR LINEAR REGRESSION IN A MODEL-FREE FRAMEWORK ⋮ StarTrek: combinatorial variable selection with false discovery rate control ⋮ Central Limit Theorem in high dimensions: The optimal bound on dimension growth rate ⋮ Estimation of smooth functionals in high-dimensional models: bootstrap chains and Gaussian approximation ⋮ Central limit theorem and bootstrap approximation in high dimensions: near \(1/\sqrt{n}\) rates via implicit smoothing

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bounding the expectation of the supremum of an empirical process over a (weak) VC-major class
• Valid post-selection inference
• Gaussian approximation of suprema of empirical processes
• Probability in Banach spaces. Isoperimetry and processes
• Rate of convergence in the central limit theorem for empirical processes
• On probabilities of large deviations in Banach spaces
• Normal approximation - some recent advances
• On the accuracy of normal approximation
• On the post selection inference constant under restricted isometry properties
• On concentration for (regularized) empirical risk minimization
• Weak convergence and empirical processes. With applications to statistics
• Bootstrapping max statistics in high dimensions: near-parametric rates under weak variance decay and application to functional and multinomial data
• Smooth approximations of the norm and differentiable functions with bounded support in Banach space \(\ell ^ k_{\infty}\)
• Gaussian approximations for maxima of random vectors under \((2+\iota)\)-th moments
• Convergence rates of least squares regression estimators with heavy-tailed errors
• Comparison and anti-concentration bounds for maxima of Gaussian random vectors
• Central limit theorems and bootstrap in high dimensions
• Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
• Large Deviations in Banach Spaces
• Bounds for the speed of convergence in the central limit theorem in C(S)
• Upper and Lower Bounds for Stochastic Processes
• A Lyapunov-type Bound in R^d

This page was built for publication: High-dimensional CLT: improvements, non-uniform extensions and large deviations