反驳带条件化的概率程序的等价性
Refuting Equivalence in Probabilistic Programs with Conditioning
AI总结:
针对带 observe 与 score 的概率程序,本文提出基于 weighted restarting 变换的等价性反驳方法,可全自动给出可证明正确的不等价判定。
摘要:
我们考虑反驳概率程序等价性的问题,即证明两个概率程序产生不同输出分布的问题。我们在带条件化的程序(即带有 observe 和 score 语句的程序)语境中研究该问题:在这类程序中,输出分布以一次运行中所有 observe 语句均求值为真的事件为条件,并且不同运行的概率密度可通过 score 语句进行更新。基于近期一项关于无条件化程序的工作,我们提出了一种面向带条件化程序的新型等价性反驳方法。该方法建立在 weighted restarting 之上,这是我们在本文中引入的一种新变换,可将带条件化的概率程序变换为输出等价的无条件化概率程序。我们的方法首次同时满足:a)完全自动化,以及 b)提供可证明正确的答案。我们在概率推断文献中的一组程序上展示了该方法的适用性。
英文摘要:
We consider the problem of refuting equivalence of probabilistic programs, i.e., the problem of proving that two probabilistic programs induce different output distributions. We study this problem in the context of programs with conditioning (i.e., with observe and score statements), where the output distribution is conditioned by the event that all the observe statements along a run evaluate to true, and where the probability densities of different runs may be updated via the score statements. Building on a recent work on programs without conditioning, we present a new equivalence refutation method for programs with conditioning. Our method is based on weighted restarting, a novel transformation of probabilistic programs with conditioning to the output equivalent probabilistic programs without conditioning that we introduce in this work. Our method is the first to be both a) fully automated, and b) providing provably correct answers. We demonstrate the applicability of our method on a set of programs from the probabilistic inference literature.
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。