An Application of Computable Distributions to the Semantics of Probabilistic Programming Languages.
ESOP(2016)
摘要
Most probabilistic programming languages for Bayesian inference give either operational semantics in terms of sampling, or denotational semantics in terms of measure-theoretic distributions. It is important that we can relate the two, given that practitioners often reason both analytically e.g.,﾿density as well as algorithmically i.e.,﾿in terms of sampling about distributions. In this paper, we give denotational semantics to a functional language extended with continuous distributions and show that by restricting attention to computable distributions, we can realize a corresponding sampling semantics.
更多查看译文
关键词
Probabilistic programs, Computable distributions, Semantics
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要