Variations and extensions of the Gaussian concentration inequality, Part II

2022/03/23 by Fresen, Daniel J.
#46N30 #60E05 #60E15 #FOS: Mathematics #Probability (math.PR) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2203.12523

Abstract

We prove concentration inequalities for f( X) about its median, where X is a random vector in ℝⁿ with independent heavy tailed coordinates of Weibull or power type, and f:ℝⁿ→ℝ is a locally Lipschitz function. This paper is part of a series of four papers, Part I, Part II and two supporting papers. It can be read independently of Part I.

Related

• Variations and extensions of the Gaussian concentration inequality, Part I
• A variance-sensitive Gaussian concentration inequality
• On the tightness of Gaussian concentration for convex functions
• Some Hoeffding- and Bernstein-type Concentration Inequalities
• Optimal constants in concentration inequalities on the sphere and in the Gauss space