Information inequalities and concentration of measure
成果类型:
Article
署名作者:
Dembo, A
署名单位:
Stanford University; Stanford University
刊物名称:
ANNALS OF PROBABILITY
ISSN/ISSBN:
0091-1798
发表日期:
1997
页码:
927-939
关键词:
product
摘要:
We derive inequalities of the form Delta(P, Q) less than or equal to H(P\R) + H(Q\R) which hold for every choice of probability measures P, Q, R, where H(P\R) denotes the relative entropy of P with respect to R acid Delta(P, Q) stands for a coupling type distance between P and Q. Using the chain rule for relative entropies and then specializing to Q with a given support we recover some of Talagrand's concentration of measure inequalities for product spaces.