arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.14864cs.ITmath.IT
收藏

整体小于部分之和:部分信息分解中的子系统不一致性

The Whole Is Less than the Sum of Parts: Subsystem Inconsistency in Partial Information Decomposition

Washington University in St. Louis(华盛顿大学圣路易斯分校)

Aobo Lyu, Andrew Clark, Netanel Raviv

AI总结:

该研究发现部分信息分解(PID)违反“整体等于部分之和”的集合论原理,提出适用于三变量系统的系统信息分解(SID)框架解决该问题,同时证明四变量及以上系统中现有格结构无法完全消除此不一致性。

摘要:

部分信息分解(Partial Information Decomposition, PID)由Williams和Beer于2010年提出,是分析多个随机变量间细粒度交互的工具,此后已在从神经科学到隐私保护的诸多领域得到应用。然而,由于关键的概念与技术挑战,统一的理论框架仍未建立。我们发现并阐明了一个核心问题:PID违反了“整体等于部分之和”(WESP)的集合论原理。通过一个三变量系统中的反例,我们演示了此类违反如何自然产生,揭示了当前基于格的PID框架的一项根本局限。为解决该问题,我们提出了一种名为系统信息分解(System Information Decomposition, SID)的新公理框架,专门针对三变量系统设计。SID通过基于协同关系重新定义分解后信息原子的求和规则,解决了WESP违反问题。但我们进一步证明,对于含四个及以上变量的系统,现有基于格的结构中没有任何部分求和方法能完全消除WESP不一致性。因此,我们的结果凸显了(反链)基于格的分解方法对一般多变量系统的固有不足。

英文摘要:

Partial Information Decomposition (PID) was proposed by Williams and Beer in 2010 as a tool for analyzing fine-grained interactions between multiple random variables, and has since found numerous applications ranging from neuroscience to privacy. However, a unified theoretical framework remains elusive due to key conceptual and technical challenges. We identify and illustrate a crucial problem: PID violates the set-theoretic principle that the whole equals the sum of its parts (WESP). Through a counterexample in a three-variable system, we demonstrate how such violations naturally arise, revealing a fundamental limitation of current lattice-based PID frameworks. To address this issue, we introduce a new axiomatic framework, termed System Information Decomposition (SID), specifically tailored for three-variable systems. SID resolves the WESP violation by redefining the summation rules of decomposed information atoms based on synergistic relationships. However, we further show that for systems with four or more variables, no partial summation approach within the existing lattice-based structures can fully eliminate WESP inconsistencies. Our results thus highlight the inherent inadequacy of (antichain) lattice-based decompositions for general multivariate systems.

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。

↑