arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.14701cs.LO
收藏

离散概率程序等价性的完备公理化

A Complete Axiomatisation of Equivalence for Discrete Probabilistic Programming

Robin Piedeleu, Mateo Torres-Ruiz, Alexandra Silva, Fabio Zanasi

AI总结:

本文引入了一个可靠且完备的等式理论来刻画离散概率程序的等价性,通过将程序转换为弦图形式的概率电路,并证明了无条件化片段及整个语言的完备性结果。

摘要:

我们引入了一个可靠且完备的等式理论,用于刻画离散概率程序的等价性,即通过扩展伯努利分布和条件化原语来建模有限事件集上分布的程序。为此,我们将这些程序转换为概率电路的图形语法,形式化为弦图,即对称幺半范畴的二维语法。接着,我们为该语法中无条件化片段的等式理论证明了首个完备性结果。最后,我们将此结果扩展为整个语言的完备等式理论。这些发展对 Markov categories 中的概率论发展也具有意义:我们的首个结果给出了 Markov kernels 范畴的生成元和方程表示,限定于二元集幂的对象。

英文摘要:

We introduce a sound and complete equational theory capturing equivalence of discrete probabilistic programs, that is, programs extended with primitives for Bernoulli distributions and conditioning, to model distributions over finite sets of events. To do so, we translate these programs into a graphical syntax of probabilistic circuits, formalised as string diagrams, the two-dimensional syntax of symmetric monoidal categories. We then prove a first completeness result for the equational theory of the conditioning-free fragment of our syntax. Finally, we extend this result to a complete equational theory for the entire language. Note these developments are also of interest for the development of probability theory in Markov categories: our first result gives a presentation by generators and equations of the category of Markov kernels, restricted to objects that are powers of the two-elements set.

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。

↑