arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.07302cs.ITmath.IT
收藏

Rényi熵和互信息的二阶矩不等式

Two-Moment Inequalities for Rényi Entropy and Mutual Information

Galen Reeves

摘要:

本文讨论了一个关于函数$r$次幂积分的二阶矩不等式的一些应用,其中$0 < r< 1$ .第一个贡献是随机向量的Rényi熵在两个不同的时刻的上界。当其中一个时刻是零阶矩时,这些边界恢复了以前基于最大熵分布的结果。更一般地说,用两个精心选择的非零矩来评估边界可以导致显着的改进,同时适度增加复杂性。第二个贡献是上界互信息的方法在某些积分相对于方差的条件密度。边界有许多有用的属性产生的方差分解的连接。

英文摘要:

This paper explores some applications of a two-moment inequality for the integral of the $r$-th power of a function, where $0 < r< 1$. The first contribution is an upper bound on the Rényi entropy of a random vector in terms of the two different moments. When one of the moments is the zeroth moment, these bounds recover previous results based on maximum entropy distributions under a single moment constraint. More generally, evaluation of the bound with two carefully chosen nonzero moments can lead to significant improvements with a modest increase in complexity. The second contribution is a method for upper bounding mutual information in terms of certain integrals with respect to the variance of the conditional density. The bounds have a number of useful properties arising from the connection with variance decompositions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑