A domain theory for statistical probabilistic programming

<p>We give an adequate denotational semantics for languages with recursive higher-order types, continuous probability distributions, and soft constraints. These are expressive languages for building Bayesian models of the kinds used in computational statistics and machine learning. Among them...

Full description

Bibliographic Details
Main Authors: Vákár, M, Kammar, O, Staton, S
Format: Conference item
Published: Association for Computing Machinery 2019