arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.05979cs.ITmath.IT
收藏

基于合作博弈的信息分解

Information Decomposition based on Cooperative Game Theory

Nihat Ay, Daniel Polani, Nathaniel Virgo

摘要:

我们提供了一种新的方法,在信息论的信息分解问题:给定一个“目标”随机变量与多个“源”变量共同分布,我们如何才能将互信息分解成一个非负的条款,量化的贡献,不仅单独,而且在组合?我们从合作博弈论中推导出我们的组成。它可以被看作是为源变量的每个组合分配“公平份额”的互信息。我们的分解是基于一个不同的格子从通常的“部分信息分解”(PID)的方法,因此,我们的分解有一个较小的数量的条款:它有类似的协同作用和独特的信息条款,但缺乏相应的冗余项。正因为如此,它能够遵守被称为“局部积极性”和“身份”的公理的等价物,这不能同时满足PID措施。

英文摘要:

We offer a new approach to the information decomposition problem in information theory: given a 'target' random variable co-distributed with multiple 'source' variables, how can we decompose the mutual information into a sum of non-negative terms that quantify the contributions of each random variable, not only individually but also in combination? We derive our composition from cooperative game theory. It can be seen as assigning a "fair share" of the mutual information to each combination of the source variables. Our decomposition is based on a different lattice from the usual 'partial information decomposition' (PID) approach, and as a consequence our decomposition has a smaller number of terms: it has analogs of the synergy and unique information terms, but lacks terms corresponding to redundancy. Because of this, it is able to obey equivalents of the axioms known as 'local positivity' and 'identity', which cannot be simultaneously satisfied by a PID measure.

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。

↑