Moderate Deviations Analysis of Binary Hypothesis Testing

被引:0
|
作者
Sason, Igal [1 ]
机构
[1] Technion Israel Inst Technol, Dept Elect Engn, IL-32000 Haifa, Israel
关键词
Concentration inequalities; hypothesis testing; moderate deviations principle; INEQUALITIES; SUMS;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This work refers to moderate-deviations analysis of binary hypothesis testing. It relies on a concentration inequality for discrete-parameter martingales with bounded jumps, which forms a refinement to the Azuma-Hoeffding inequality. Relations of the analysis to the moderate deviations principle for i.i.d. random variables and the relative entropy are considered.
引用
下载
收藏
页码:821 / 825
页数:5
相关论文
共 50 条