Fisher information inequalities and the central limit theorem

Fisher information inequalities and the central limit theorem
复制标题

费舍尔信息不等式和中心极限定理

DOI:
--
复制
发表时间:
2001
期刊:
影响因子:
--
通讯作者:
A. Barron
A. Barron
中科院分区:
--
文献类型:
--
作者:
O. Johnson;A. Barron

文献摘要

被引文献

相似文献

本文给出了中心极限定理中Fisher信息和相对熵的收敛速度为O(1/n)的条件。我们利用L2空间中的投影理论和Poincaré不等式,对巴伦和Brown的结果所隐含的Fisher信息的减少提供了更好的理解。我们表明,如果标准化的Fisher信息变得有限,那么它收敛到零。
Abstract.We give conditions for an O(1/n) rate of convergence of Fisher information and relative entropy in the Central Limit Theorem. We use the theory of projections in L2 spaces and Poincaré inequalities, to provide a better understanding of the decrease in Fisher information implied by results of Barron and Brown. We show that if the standardized Fisher information ever becomes finite then it converges to zero.