Variations and extensions of the Gaussian concentration inequality, Part I

2018/12/28 by Daniel J. Fresen, Fresen, Daniel J. · 1 citation
Computer Science · Mathematics · #52A27 #52A30 #60E05 #60E15 #Distributed Sensor Networks and Detection Algorithms #FOS: Mathematics #Probability (math.PR) #Statistical Distribution Estimation and Applications

paper · pdf · doi:10.48550/arxiv.1812.10938

openalex publication_date 2018/12/28 · openalex created_date 2022/08/01 · openalex updated_date 2026/07/28

Abstract

The classical Gaussian concentration inequality for Lipschitz functions is adapted to a setting where the classical assumptions (i.e. Lipschitz and Gaussian) are not met. The theory is more direct than much of the existing theory designed to handle related generalizations. An application is presented to linear combinations of heavy tailed random variables.

Cited by

• Concentration of the truncated variation of fractional Brownian motions of any Hurst index, their 1/H-variations and local times

Related

• Variations and extensions of the Gaussian concentration inequality, Part II
• A variance-sensitive Gaussian concentration inequality
• Concentration of Lipschitz Functions of Negatively Dependent Variables
• A covariance representation and an elementary proof of the Gaussian concentration inequality
• Some Hoeffding- and Bernstein-type Concentration Inequalities