Bounding $\bar{d}$-distance by informational divergence: a method to prove measure concentration
Bounding $\bar{d}$-distance by informational divergence: a method to prove measure concentration
复制标题
DOI：
10.1214/aop/1039639365
复制
发表时间：
1996-04
影响因子：
2.3
通讯作者：
K. Marton
中科院分区：
文献类型：
--
作者：
K. Marton
Pinsker给出了定义在任意概率空间上的概率测度的变分距离与信息散度之间的一个简单不等式。我们将考虑从可数字母表中提取的序列的概率测度，并从Pinsker不等式中推导出信息发散的d距离的界。这种界可以用来证明某些非乘积分布的测度集中现象。
There is a simple inequality by Pinsker between variational distance and informational divergence of probability measures defined on arbitrary probability spaces. We shall consider probability measures on sequences taken from countable alphabets, and derive, from Pinsker's inequality, bounds on the d-distance by informational divergence. Such bounds can be used to prove the concentration of measure phenomenon for some nonproduct distributions.