arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.06555cs.ITmath.ITmath.PR
收藏

关于Renyi熵权不等式

On Renyi Entropy Power Inequalities

Eshed Ram, Igal Sason

摘要:

给出了改进的Rényi熵幂不等式(R-EPI).考虑在$\mathbb{R}^d$上取值的$n$个独立连续随机向量的和$S_n = \sum_{k=1}^n X_k$,并设$α\in [1, \infty]$。R-EPI提供了$S_n$的$α$阶Rényi熵功率的下限,直到乘法常数(其通常可以取决于$n, α, d$),该下限等于$n$随机向量$\{X_k\}_{k=1}^n$的$α$阶Rényi熵功率之和。对于$α=1$,R-EPI与著名的香农熵功率不等式一致。第一个改进的R-EPI是在Bobkov和Chistyakov最近的R-EPI的基础上,利用锐化的Young不等式得到的。R-EPI的进一步改进还依赖于凸优化和实值对角矩阵的秩一修改的结果。

英文摘要:

This paper gives improved Rényi entropy power inequalities (R-EPIs). Consider a sum $S_n = \sum_{k=1}^n X_k$ of $n$ independent continuous random vectors taking values on $\mathbb{R}^d$, and let $α\in [1, \infty]$. An R-EPI provides a lower bound on the order-$α$ Rényi entropy power of $S_n$ that, up to a multiplicative constant (which may depend in general on $n, α, d$), is equal to the sum of the order-$α$ Rényi entropy powers of the $n$ random vectors $\{X_k\}_{k=1}^n$. For $α=1$, the R-EPI coincides with the well-known entropy power inequality by Shannon. The first improved R-EPI is obtained by tightening the recent R-EPI by Bobkov and Chistyakov which relies on the sharpened Young's inequality. A further improvement of the R-EPI also relies on convex optimization and results on rank-one modification of a real-valued diagonal matrix.

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。

↑