An information inequality for the Bayes risk
An information inequality for the Bayes risk
复制标题
贝叶斯风险的信息不平等
DOI：
10.1214/aos/1069362323
复制
发表时间：
1996
影响因子：
4.5
通讯作者：
M. Akahira
中科院分区：
文献类型：
--
作者：
M. Sato;M. Akahira
本文从二次损失下贝叶斯风险关于截断先验的信息不等式出发，给出了一个下界。在Brown和Gajek的正则性条件并不总是满足的情况下进行了讨论。给出了极小极大风险的一个相关结果。
This paper presents a lower bound, derived from the information inequality for the Bayes risk with respect to truncated priors under quadratic loss. It is discussed in cases where the regularity condition of Brown and Gajek is not always satisfied. A related result for the minimax risk is also given.