arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.07805cs.ITmath.IT
收藏

关于可提取的共享信息

On extractable shared information

Johannes Rauh, Pradeep Kr. Banerjee, Eckehard Olbrich, Jürgen Jost, Nils Bertschinger

摘要:

考虑一对随机变量$X_{1},X_{2}$关于另一个变量$S$共享的信息的量化问题。我们提出了一个新的措施共享信息,称为可提取的共享信息,这是左单调的,也就是说,共享的信息约$S$是有界的从下到上的信息共享约$f(S)$的任何功能$f$。我们表明,我们的措施导致一个新的非负分解的互信息$I(S;X_1X_2)$共享,互补和独特的组件。我们研究了这种分解的性质,并表明左单调共享信息与布莱克威尔对唯一信息的解释不兼容。我们还讨论了是否有可能有一个分解,其中共享和唯一的信息是左单调。

英文摘要:

We consider the problem of quantifying the information shared by a pair of random variables $X_{1},X_{2}$ about another variable $S$. We propose a new measure of shared information, called extractable shared information, that is left monotonic; that is, the information shared about $S$ is bounded from below by the information shared about $f(S)$ for any function $f$. We show that our measure leads to a new nonnegative decomposition of the mutual information $I(S;X_1X_2)$ into shared, complementary and unique components. We study properties of this decomposition and show that a left monotonic shared information is not compatible with a Blackwell interpretation of unique information. We also discuss whether it is possible to have a decomposition in which both shared and unique information are left monotonic.

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。

↑