arXiv Analytics

Sign in

arXiv:2203.12523 [math.PR]AbstractReferencesReviewsResources

Variations and extensions of the Gaussian concentration inequality, Part II

Daniel J. Fresen

Published 2022-03-23Version 1

Pisier's version of the Gaussian concentration inequality is transformed and used to prove deviation inequalities for locally Lipschitz functions with respect to heavy tailed product measures on Euclidean space. The approach is, in our opinion, more direct than much of the modern theory of concentration of measure (i.e. Poincar\'{e} and log-Sobolev inequalities, estimating moments etc.).

Comments: 34 pages. The original paper, which was uploaded as a separate submission (arXiv:1812.10938), has been split into two papers, Part I and Part II; this is Part II
Categories: math.PR, math.ST, stat.TH
Subjects: 60E05, 60E15, 46N30
Related articles: Most relevant | Search more
arXiv:2207.01867 [math.PR] (Published 2022-07-05)
Variations and extensions of the Gaussian concentration inequality, Part IIa: Special case
arXiv:1812.10938 [math.PR] (Published 2018-12-28)
Variations and extensions of the Gaussian concentration inequality
arXiv:1904.03674 [math.PR] (Published 2019-04-07)
An improved bound for the Gaussian concentration inequality

Links

Toolbox