Tight lower bound on the probability of a binomial exceeding Cross Mark its expectation

被引:31
|
作者
Greenberg, Spencer [1 ]
Mohri, Mehryar [1 ,2 ]
机构
[1] Courant Inst Math Sci, New York, NY 10012 USA
[2] Google Res, New York, NY 10011 USA
关键词
Binomial distribution; Lower bound; Expected value; Relative deviation; Machine learning;
D O I
10.1016/j.spl.2013.12.009
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 give the proof of a tight lower bound on the probability that a binomial random variable exceeds its expected value. The inequality plays an important role in a variety of contexts, including the analysis of relative deviation bounds in learning theory and generalization bounds for unbounded loss functions. (C) 2013 Elsevier B.V. All rights reserved.
引用
收藏
页码:91 / 98
页数:8
相关论文
共 11 条