A convenient category for higher-order probability theory

A convenient category for higher-order probability theory
复制标题

高阶概率论的便捷范畴

DOI:
10.1109/lics.2017.8005137
复制
发表时间:
2017
期刊:
--
影响因子:
--
通讯作者:
Heunen C
Heunen C
中科院分区:
--
文献类型:
--
作者:
Heunen C

文献摘要

参考文献

被引文献

相似文献

高阶概率编程语言允许程序员以简洁和结构化的方式编写机器学习和统计中的复杂模型,但超越了概率论的标准度量论形式化。程序可以同时使用高阶函数和连续分布,甚至可以定义函数的概率分布。但标准概率论不能很好地处理高阶函数:可测空间的范畴不是笛卡尔闭集的。这里我们引入拟Borel空间。我们证明了这些空间:形成了取代可测空间的概率论的新形式;形成了笛卡儿闭范畴,从而支持高阶函数;形成了良点范畴,从而支持了等式推理的良好证明原则;以及支持连续概率分布。我们证明了拟Borel空间在高阶函数和概率中的应用:证明了包含随机函数的概率论的一个著名构造获得了更清晰的表达式;并将概率论中的一个关键定理de Finetti定理推广到拟Borel空间。
Higher-order probabilistic programming languages allow programmers to write sophisticated models in machine learning and statistics in a succinct and structured way, but step outside the standard measure-theoretic formalization of probability theory. Programs may use both higher-order functions and continuous distributions, or even define a probability distribution on functions. But standard probability theory does not handle higher-order functions well: the category of measurable spaces is not cartesian closed. Here we introduce quasi-Borel spaces. We show that these spaces: form a new formalization of probability theory replacing measurable spaces; form a cartesian closed category and so support higher-order functions; form a well-pointed category and so support good proof principles for equational reasoning; and support continuous probability distributions. We demonstrate the use of quasi-Borel spaces for higher-order functions and probability by: showing that a well-known construction of probability theory involving random functions gains a cleaner expression; and generalizing de Finetti's theorem, that is a crucial theorem in probability theory, to quasi-Borel spaces.
基础量子力学中的可计算性
DOI: 10.23638/lmcs-14(2:14)2018
发表时间: 2016
期刊: ArXiv
影响因子: --
作者:
Martin Pape;T. Streicher
通讯作者: T. Streicher
功能空间的 Borel 结构
DOI: 10.1215/ijm/1255631584
发表时间: 1961
影响因子: 0.6
作者:
R. Aumann
通讯作者: R. Aumann
DOI: 10.1145/2951913.2951942
发表时间: 2015-12
期刊: Proceedings of the 21st ACM SIGPLAN International Conference on Functional Programming
影响因子: --
作者:
J. Borgström;Ugo Dal Lago;A. Gordon;Marcin Szymczak
通讯作者: J. Borgström;Ugo Dal Lago;A. Gordon;Marcin Szymczak
关于标准 Borel 和相关空间的一些注释
DOI: --
发表时间: 2008
期刊:
影响因子: --
作者:
C. Preston
通讯作者: C. Preston
DOI: --
发表时间: 2014
影响因子: 1.1
作者:
M. Mislove
通讯作者: M. Mislove