arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09085cs.AI
收藏

可处理概率电路的多项式语义

Polynomial Semantics of Tractable Probabilistic Circuits

University of California Los Angeles(加州大学洛杉矶分校)

Oliver Broadrick, Honghua Zhang, Guy Van den Broeck

AI总结:

本文证明二元变量上多种概率电路多项式语义可在多项式规模内相互转换,从而具有相同的边缘推断可处理性,并证明其向类别变量的扩展会使推断变为 #P-hard。

摘要:

概率电路计算表示多元概率分布的多线性多项式。它们是支持高效边缘推断的可处理模型。然而,文献中已考虑了多种多项式语义(例如网络多项式、似然多项式、生成函数和傅里叶变换)。这些分布的多项式编码的电路表示之间的关系在很大程度上是未知的。在本文中,我们证明对于二元变量上的分布,这些概率电路模型中的每一个都是等价的,即其中任意一个的电路都可以转换为其他任意一个的电路,且规模仅增加多项式倍。因此,它们在同一类分布上对于边缘推断都是可处理的。最后,我们探索了一种此类多项式语义(称为概率生成电路)向类别随机变量的自然扩展,并确定推断变为 #P-hard。

英文摘要:

Probabilistic circuits compute multilinear polynomials that represent multivariate probability distributions. They are tractable models that support efficient marginal inference. However, various polynomial semantics have been considered in the literature (e.g., network polynomials, likelihood polynomials, generating functions, and Fourier transforms). The relationships between circuit representations of these polynomial encodings of distributions is largely unknown. In this paper, we prove that for distributions over binary variables, each of these probabilistic circuit models is equivalent in the sense that any circuit for one of them can be transformed into a circuit for any of the others with only a polynomial increase in size. They are therefore all tractable for marginal inference on the same class of distributions. Finally, we explore the natural extension of one such polynomial semantics, called probabilistic generating circuits, to categorical random variables, and establish that inference becomes #P-hard.

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。

↑