An error bound in the Sudakov-Fernique inequality

2005/10/20 by Sourav Chatterjee, Chatterjee, Sourav · 4 citations
Computer Science · Decision Sciences · Mathematics · #Bayesian Methods and Mixture Models #FOS: Mathematics #Probability (math.PR) #Probability and Risk Models #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.math/0510424

openalex publication_date 2005/10/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We obtain an asymptotically sharp error bound in the classical Sudakov-Fernique comparison inequality for finite collections of gaussian random variables. Our proof is short and self-contained, and gives an easy alternative argument for the classical inequality, extended to the case of non-centered processes.

Cited by

• Sublinear Optimal Policy Value Estimation in Contextual Bandits
• The Structure of Extremal Bad Science Matrices
• Gaussian Multiplier Bootstrap Procedure for the κth Largest Coordinate of High-Dimensional Statistics
• Non-negative Principal Component Analysis: Message Passing Algorithms\n and Sharp Asymptotics

Related

• Sudakov-Fernique post-AMP, and a new proof of the local convexity of the TAP free energy
• Comparison and anti-concentration bounds for maxima of Gaussian random vectors
• Moment Inequalities for Suprema of Gaussian Random Processes
• A Gordon-Chevet type Inequality
• Density estimates and concentration inequalities with Malliavin calculus