A tail inequality for quadratic forms of subgaussian random vectors

被引：53

作者：

Hsu, Daniel ^{[1
]}

Kakade, Sham M. ^{[1
]}

Zhang, Tong ^{[2
]}

机构：

[1] Microsoft Res New England, Cambridge, MA USA

[2] Rutgers State Univ, Dept Stat, Piscataway, NJ 08855 USA

来源：

ELECTRONIC COMMUNICATIONS IN PROBABILITY | 2012年 / 17卷

关键词：

Tail inequality; quadratic form; subgaussian random vectors; subgaussian chaos;

D O I：

10.1214/ECP.v17-2079

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

This article proves an exponential probability tail inequality for positive semidefinite quadratic forms in a subgaussian random vector. The bound is analogous to one that holds when the vector has independent Gaussian entries.

引用

页码：1 / 6

页数：6