TY - SLIDE
TI - Diffeological Spaces and Denotational Semantics for Differential Programming
A2 - Kammar, Ohad
A2 - Staton, Sam
A2 - Vákár, Matthijs
DA - 2018///
PY - 2018
LA - en
KW - Automatic differentiation
KW - Differentiation
KW - Programming language theory
ER -
TY - JOUR
TI - A Domain Theory for Statistical Probabilistic Programming
AU - Vákár, Matthijs
AU - Kammar, Ohad
AU - Staton, Sam
T2 - arXiv:1811.04196 [cs]
AB - 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. Our new semantic model is based on `quasi-Borel predomains'. These are a mixture of chain-complete partial orders (cpos) and quasi-Borel spaces. Quasi-Borel spaces are a recent model of probability theory that focuses on sets of admissible random elements. Probability is traditionally treated in cpo models using probabilistic powerdomains, but these are not known to be commutative on any class of cpos with higher order functions. By contrast, quasi-Borel predomains do support both a commutative probabilistic powerdomain and higher-order functions. As we show, quasi-Borel predomains form both a model of Fiore's axiomatic domain theory and a model of Kock's synthetic measure theory.
DA - 2018/11/10/
PY - 2018
DP - arXiv.org
UR - http://arxiv.org/abs/1811.04196
Y2 - 2019/10/10/11:49:16
ER -
TY - JOUR
TI - Denotational validation of higher-order Bayesian inference
AU - Ścibior, Adam
AU - Kammar, Ohad
AU - Vákár, Matthijs
AU - Staton, Sam
AU - Yang, Hongseok
AU - Cai, Yufei
AU - Ostermann, Klaus
AU - Moss, Sean K.
AU - Heunen, Chris
AU - Ghahramani, Zoubin
T2 - Proceedings of the ACM on Programming Languages
AB - 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.
DA - 2017/12/27/
PY - 2017
DO - 10.1145/3158148
DP - arXiv.org
VL - 2
IS - POPL
SP - 1
EP - 29
J2 - Proc. ACM Program. Lang.
SN - 24751421
UR - http://arxiv.org/abs/1711.03219
Y2 - 2019/10/10/11:49:49
ER -