Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Orlicz norms and concentration inequalities for β-heavy tailed random variables

Abstract : We establish a new concentration-of-measure inequality for the sum of independent random variables with β-heavy tail. This includes exponential of Gaussian distributions (a.k.a. log-normal distributions), or exponential of Weibull distributions, among others. These distributions have finite polyno- mial moments at any order but may not have finite α-exponential moments. We exhibit a Orlicz norm adapted to this setting of β-heavy tails, we prove a new Talagrand inequality for the sum and a new maximal inequality. As consequence, a bound on the deviation probability of the sum from its mean is obtained, as well as a bound on uniform deviation probability.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Emmanuel Gobet <>
Submitted on : Wednesday, April 21, 2021 - 11:36:05 PM
Last modification on : Saturday, July 3, 2021 - 3:46:19 AM


Files produced by the author(s)


  • HAL Id : hal-03175697, version 2


Linda Chamakh, Emmanuel Gobet, Wenjun Liu. Orlicz norms and concentration inequalities for β-heavy tailed random variables. 2021. ⟨hal-03175697v2⟩



Record views


Files downloads