Subgaussian and strictly subgaussian random variable

Abstract

We study in this report the so-called Strictly Subgaussian (SSub) random variables (r.v.), which form a very interest subclass of Subgaussian (Sub) r.v., and obtain the exact exponential bounds for tail of distribution for sums of independent and disjoint such a variables, not necessary to be identical distributed, and give some new examples of SSub variables to show the exactness of our estimates. We extend also these results on the case of sums of subgaussian martingale differences, and show that the mixture of (Strictly) Subgaussian r.v. forms also (Strictly) subgaussian variable.

References in corpus (6)

• Large Deviation Methods for Approximate Probabilistic Inference
• Exact inequalities for sums of asymmetric random variables, with applications
• Exact value for subgaussian norm of centered indicator random variable
• On the probabilistic Cauchy theory of the cubic nonlinear Schrödinger equation on ${\mathbb{R}}^d$, $d\ge 3$
• The Kearns--Saul inequality for Bernoulli and Poisson-binomial distributions
• A full proof of universal inequalities for the distribution function of the binomial law

Cited by in corpus (4)

• Non-uniform non-asymptotical sharp estimate for the rate of convergence for Bernstein's polynomial approximation, with bilateral constant evaluation
• Lower boundaries for parametric estimations in different norms
• Generalized Bernstein-type approximation of continuous functions
• Grand Lebesgue norm estimation for binary random variables, with applications