Resource type

Commutative Semantics for Probabilistic Programming

Resource type
Authors/contributors
Title
Commutative Semantics for Probabilistic Programming
Abstract
We show that a measure-based denotational semantics for probabilistic programming is commutative. The idea underlying probabilistic programming languages (Anglican, Church, Hakaru, ...) is that programs express statistical models as a combination of prior distributions and likelihood of observations. The product of prior and likelihood is an unnormalized posterior distribution, and the inference problem is to find the normalizing constant. One common semantic perspective is thus that a probabilistic program is understood as an unnormalized posterior measure, in the sense of measure theory, and the normalizing constant is the measure of the entire semantic domain.
Book Title
Programming Languages and Systems
Volume
10201
Place
Berlin, Heidelberg
Publisher
Springer Berlin Heidelberg
Date
2017
Pages
855-879
Language
en
ISBN
978-3-662-54433-4 978-3-662-54434-1
Accessed
2019-11-23T16:35:50Z
Library Catalog
Crossref
Extra
ZSCC: NoCitationData[s0] DOI: 10.1007/978-3-662-54434-1_32
Citation
Staton, S. (2017). Commutative Semantics for Probabilistic Programming. In H. Yang (Ed.), Programming Languages and Systems (Vol. 10201, pp. 855–879). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-662-54434-1_32
PROBABILITY & STATISTICS
Processing time: 0.02 seconds

Graph of references

(from Zotero to Gephi via Zotnet with this script)
Graph of references