Exchangeability is a central notion in statistics and probability theory. The assumption that an infinite sequence of data points is exchangeable is at the core of Bayesian statistics. However, finite exchangeability as a statistical property that renders probabilistic inference tractable is less well-understood. We develop a theory of finite exchangeability and its relation to tractable probabilistic inference. The theory is complementary to that of independence and conditional independence. We show that tractable inference in probabilistic models with high treewidth and millions of variables can be understood using the notion of finite (partial) exchangeability. We also show that existing lifted inference algorithms implicitly utilize a combination of conditional independence and partial exchangeability.
Hybrid Probabilistic Inference with Logical Constraints: Tractability and Message Passing
University of California, LA(加利福尼亚大学洛杉矶分校);AMSS(数学与系统科学研究院);Chinese Academy of Sciences(中国科学院);DISI(信息工程与计算机科学系);University of Trento(特伦托大学)
加权模型集成(Weighted Model Integration,简称WMM)是一个非常吸引人的概率推理框架:它允许通过可满足性模理论(Satisfiability Modulo Theories,简称SMT)的语言来表达真实世界混合场景的复杂依赖关系,其中变量在本质上是异构的(包括连续和离散);以及计算具有任意复杂逻辑约束的概率查询。最近的工作表明,在某些假设下,可简化的模型集成(MI)问题,从而有效地允许混合概率推理的体积计算。在本文中,我们介绍了一种新的制定MI通过消息传递计划,允许有效地计算的边际密度和统计矩的所有变量在线性时间。因此,当任意丰富的MI查询符合问题结构时,我们能够摊销推理,这里表示为与SMT公式相关联的原始图。此外,我们从理论上跟踪的易处理边界的确切MI。事实上,我们证明,在原始图的结构要求,使我们的MI算法易于处理-边界的直径和树宽-边界不仅是足够的,但通过MI易于推理的必要条件。
Tractable Representation Learning with Probabilistic Circuits
Technische Universität Darmstadt(达姆施塔特工业大学);University of Texas, Dallas(德克萨斯大学达拉斯分校);University of Edinburgh(爱丁堡大学);Universität Bremen(不来梅大学);University of Texas at Dallas(德克萨斯大学达拉斯分校)
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院)