Learning sub-Gaussianity
演讲者
Huiming Zhang
时间
2024年12月17日 09:00 至 10:30
地点
Online
线上
Zoom 518 868 7656
(BIMSA)
摘要
In the era of AI, the variance-type parameters of sub-Gaussian distributions are of paramount importance in upper confidence bound bandit algorithms and non-asymptotic statistical inferences. However, directly estimating these parameters using the empirical moment generating function is infeasible. To address this, we suggest using the sub-Gaussian intrinsic moment norm achieved by maximizing a sequence of normalized moments. In practice, we offer an intuitive method for checking sub-Gaussian data with a finite sample size using the sub-Gaussian plot. Intrinsic moment norm can be robustly estimated via a simple plug-in approach. Our theoretical findings are also applicable to the multi-armed bandit scenario.