arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1711.03219cs.PL
收藏

高阶贝叶斯推理的指称验证

Denotational validation of higher-order Bayesian inference

Adam Ścibior, Ohad Kammar, Matthijs Vákár, Sam Staton, Hongseok Yang, Yufei Cai, Klaus Ostermann, Sean K. Moss, Chris Heunen, Zoubin Ghahramani

摘要:

我们提出了一个模块化的概率程序设计语言,用于数据科学和机器学习的贝叶斯推理算法的语义帐户。复杂的推理算法通常用较小部分的组合来解释。然而,无论是理论上的理由,他们的实施反映了这种模块化。我们将展示如何概念化和分析这样的推理算法操纵的概率程序使用高阶函数和归纳类型,其指称语义的中间表示。连续分布的语义账户使用可测量空间。然而,我们使用高阶函数提出了一个实质性的技术困难:它是不可能定义一个可测空间结构的集合之间的可测函数的任意可测空间,是兼容的标准操作,这些功能,如功能的应用。我们克服了这个困难,使用准Borel空间,最近提出的数学结构,支持函数空间和连续分布。我们定义了一类表示概率程序的语义结构,以及这些表示在分布保持方面的变换的语义有效性标准。我们开发了一系列用于组成表示的构建块。我们使用这些构建块来验证常见的推理算法,如顺序蒙特卡罗和马尔可夫链蒙特卡罗。为了强调语义操纵与其传统测量理论渊源之间的联系,我们使用了科克的综合测量理论。我们证明了它的有用性,证明了准博雷尔对应的大都会黑斯廷斯-格林定理。

英文摘要:

We present a modular semantic account of Bayesian inference algorithms for probabilistic programming languages, as used in data science and machine learning. Sophisticated inference algorithms are often explained in terms of composition of smaller parts. However, neither their theoretical justification nor their implementation reflects this modularity. We show how to conceptualise and analyse such inference algorithms as manipulating intermediate representations of probabilistic programs using higher-order functions and inductive types, and their denotational semantics. Semantic accounts of continuous distributions use measurable spaces. However, our use of higher-order functions presents a substantial technical difficulty: it is impossible to define a measurable space structure over the collection of measurable functions between arbitrary measurable spaces that is compatible with standard operations on those functions, such as function application. We overcome this difficulty using quasi-Borel spaces, a recently proposed mathematical structure that supports both function spaces and continuous distributions. We define a class of semantic structures for representing probabilistic programs, and semantic validity criteria for transformations of these representations in terms of distribution preservation. We develop a collection of building blocks for composing representations. We use these building blocks to validate common inference algorithms such as Sequential Monte Carlo and Markov Chain Monte Carlo. To emphasize the connection between the semantic manipulation and its traditional measure theoretic origins, we use Kock's synthetic measure theory. We demonstrate its usefulness by proving a quasi-Borel counterpart to the Metropolis-Hastings-Green theorem.

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。

↑