Denotational Validation of Higher-order Bayesian Inference

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 471
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorScibior, Adamko
dc.contributor.authorKammar, Ohadko
dc.contributor.authorVakar, Matthijsko
dc.contributor.authorStaton, Samko
dc.contributor.authorYang, Hongseokko
dc.contributor.authorCai, Yufeiko
dc.contributor.authorOstermann, Klausko
dc.contributor.authorMoss, Seanko
dc.contributor.authorHeunen, Chrisko
dc.contributor.authorGhahramani, Zoubinko
dc.identifier.citationProceedings of the ACM on Programming Languages, v.2-
dc.description.abstractWe 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.-
dc.titleDenotational Validation of Higher-order Bayesian Inference-
dc.citation.publicationnameProceedings of the ACM on Programming Languages-
dc.contributor.localauthorYang, Hongseok-
dc.contributor.nonIdAuthorScibior, Adam-
dc.contributor.nonIdAuthorKammar, Ohad-
dc.contributor.nonIdAuthorVakar, Matthijs-
dc.contributor.nonIdAuthorStaton, Sam-
dc.contributor.nonIdAuthorCai, Yufei-
dc.contributor.nonIdAuthorOstermann, Klaus-
dc.contributor.nonIdAuthorMoss, Sean-
dc.contributor.nonIdAuthorHeunen, Chris-
dc.contributor.nonIdAuthorGhahramani, Zoubin-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0