概率质量排除与逐点互信息的有向分量
Probability Mass Exclusions and the Directed Components of Pointwise Mutual Information
摘要:
本文研究了如何从一个随机变量的事件提供逐点互信息从另一个变量通过概率质量排除事件。我们首先介绍概率质量图,它提供了一个直观的表示如何通过排除将先验分布转换为后验分布。借助这些图表,我们确定了两种不同类型的概率质量排除-即信息和错误信息排除。然后,由Fano的推导逐点互信息的动机,我们提出了四个假设,旨在将逐点互信息分解成两个独立的信息成分:一个非负项与信息排除和一个非正项与错误信息排除。这产生了一个新的衍生物的逐点互信息到熵分量的熟悉的分解。最后,我们讨论的相关性,考虑信息的概率质量排除正在进行的努力分解多元信息。
英文摘要:
This paper examines how an event from one random variable provides pointwise mutual information about an event from another variable via probability mass exclusions. We start by introducing probability mass diagrams, which provide a visual representation of how a prior distribution is transformed to a posterior distribution through exclusions. With the aid of these diagrams, we identify two distinct types of probability mass exclusions---namely informative and misinformative exclusions. Then, motivated by Fano's derivation of the pointwise mutual information, we propose four postulates which aim to decompose the pointwise mutual information into two separate informational components: a non-negative term associated with the informative exclusion and a non-positive term associated with the misinformative exclusions. This yields a novel derivation of a familiar decomposition of the pointwise mutual information into entropic components. We conclude by discussing the relevance of considering information in terms of probability mass exclusions to the ongoing effort to decompose multivariate information.
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。