Litcius/Paper detail

Sub‐Weibull distributions: Generalizing sub‐Gaussian and sub‐Exponential properties to heavier tailed distributions

Mariia Vladimirova, Stéphane Girard, Hien Nguyen, Julyan Arbel

2020Stat32 citationsDOIOpen Access PDF

Abstract

We propose the notion of sub‐Weibull distributions, which are characterized by tails lighter than (or equally light as) the right tail of a Weibull distribution. This novel class generalizes the sub‐Gaussian and sub‐Exponential families to potentially heavier tailed distributions. Sub‐Weibull distributions are parameterized by a positive tail index θ and reduce to sub‐Gaussian distributions for and to sub‐Exponential distributions for . A characterization of the sub‐Weibull property based on moments and on the moment generating function is provided and properties of the class are studied. An estimation procedure for the tail parameter is proposed and is applied to an example stemming from Bayesian deep learning.

Topics & Concepts

MathematicsClass (philosophy)Moment (physics)Weibull distributionProperty (philosophy)Parameterized complexityCharacterization (materials science)Function (biology)Probability distributionStatistical physicsMoment-generating functionHeavy-tailed distributionK-distributionInverse distributionApplied mathematicsBayesian probabilityDistribution (mathematics)Statistical parameterProbability density functionCombinatoricsNatural exponential familyDistribution functionStability (learning theory)Scale parameterStatisticsGenerating functionRandom variablePure mathematicsDiscrete mathematicsScale (ratio)Statistical modelStatistical Distribution Estimation and ApplicationsStatistical Mechanics and EntropyBayesian Methods and Mixture Models