Conference item icon

Conference item

A domain theory for statistical probabilistic programming

Abstract:

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 are untyped languages, similar to Church and WebPPL, because our semantics allows recursive mixed-variance datatypes. Our semantics justifies important program equivalences including commutativity.

<...> Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1145/3290349

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
Balliol College
Role:
Author
ORCID:
0000-0002-2071-0929
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Computer Science
Oxford college:
Jesus College
Role:
Author
More from this funder
Grant:
Career Development Fellowship
More from this funder
Grant:
University Resarch Fellowship
Publisher:
Association for Computing Machinery Publisher's website
Journal:
46th ACM SIGPLAN Symposium on Principles of Programming Languages Journal website
Volume:
3
Issue:
POPL
Article number:
36
Host title:
Proceedings of the ACM on Programming Languages
Publication date:
2019-01-02
Acceptance date:
2018-11-09
DOI:
EISSN:
2475-1421
ISSN:
2475-1421
Source identifiers:
941031
Keywords:
Pubs id:
pubs:941031
UUID:
uuid:32d978e8-4a2a-4efb-915d-1e04c98d4502
Local pid:
pubs:941031
Deposit date:
2018-11-12

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP