# Your search

PROBABILITY & STATISTICS

PROGRAMMING LANGUAGES

## Denotational validation of higher-order Bayesian inference

Resource type

Authors/contributors

- Ścibior, Adam (Author)
- Kammar, Ohad (Author)
- Vákár, Matthijs (Author)
- Staton, Sam (Author)
- Yang, Hongseok (Author)
- Cai, Yufei (Author)
- Ostermann, Klaus (Author)
- Moss, Sean K. (Author)
- Heunen, Chris (Author)
- Ghahramani, Zoubin (Author)

Title

Denotational validation of higher-order Bayesian inference

Abstract

We present a modular semantic account of Bayesian inference algorithms for probabilistic programming languages, as used in data science and machine learning. Sophisticated inference algorithms are often explained in terms of composition of smaller parts. However, neither their theoretical justification nor their implementation reflects this modularity. We show how to conceptualise and analyse such inference algorithms as manipulating intermediate representations of probabilistic programs using higher-order functions and inductive types, and their denotational semantics. Semantic accounts of continuous distributions use measurable spaces. However, our use of higher-order functions presents a substantial technical difficulty: it is impossible to define a measurable space structure over the collection of measurable functions between arbitrary measurable spaces that is compatible with standard operations on those functions, such as function application. We overcome this difficulty using quasi-Borel spaces, a recently proposed mathematical structure that supports both function spaces and continuous distributions. We define a class of semantic structures for representing probabilistic programs, and semantic validity criteria for transformations of these representations in terms of distribution preservation. We develop a collection of building blocks for composing representations. We use these building blocks to validate common inference algorithms such as Sequential Monte Carlo and Markov Chain Monte Carlo. To emphasize the connection between the semantic manipulation and its traditional measure theoretic origins, we use Kock's synthetic measure theory. We demonstrate its usefulness by proving a quasi-Borel counterpart to the Metropolis-Hastings-Green theorem.

Publication

Proceedings of the ACM on Programming Languages

Volume

2

Issue

POPL

Pages

1-29

Date

2017-12-27

Journal Abbr

Proc. ACM Program. Lang.

DOI

10.1145/3158148

ISSN

24751421

Accessed

2019-10-10T11:49:49Z

Library Catalog

Extra

arXiv: 1711.03219

Citation

Ścibior, A., Kammar, O., Vákár, M., Staton, S., Yang, H., Cai, Y., … Ghahramani, Z. (2017). Denotational validation of higher-order Bayesian inference.

*Proceedings of the ACM on Programming Languages*,*2*(POPL), 1–29. https://doi.org/10.1145/3158148
PROBABILITY & STATISTICS

PROGRAMMING LANGUAGES

Link to this record