Concentration inequalities for set-indexed empirical processes

被引:0
|
作者
Rio, E [1 ]
机构
[1] Univ Versailles, EP 1755 CNRS, F-78035 Versailles, France
关键词
D O I
10.1007/PL00008756
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
We propose new concentration inequalities for maxims of set-indexed empirical processes. Out approach is based either on entropy inequalities or on martingale methods. The improvements we get concern the rate function which is exactly the large deviations rate function of a binomial law in most of the cases.
引用
收藏
页码:163 / 175
页数:13
相关论文
共 50 条