Compositional Semantics for Probabilistic Programs with Exact Conditioning
arXiv:2101.11351
Abstract
We define a probabilistic programming language for Gaussian random variables with a first-class exact conditioning construct. We give operational, denotational and equational semantics for this language, establishing convenient properties like exchangeability of conditions. Conditioning on equality of continuous random variables is nontrivial, as the exact observation may have probability zero; this is Borel's paradox. Using categorical formulations of conditional probability, we show that the good properties of our language are not particular to Gaussians, but can be derived from universal properties, thus generalizing to wider settings. We define the Cond construction, which internalizes conditioning as a morphism, providing general compositional semantics for probabilistic programming with exact conditioning.
arXiv comment16 pages, 5 figures
References in corpus (9)
- A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
- Disintegration and Bayesian Inversion via String Diagrams
- Representable Markov Categories and Comparison of Statistical Experiments in Categorical Probability
- Profunctor Optics, a Categorical Update
- On computability and disintegration
- Universal Properties in Quantum Theory
- Bayesian Updates Compose Optically
- The Beta-Bernoulli process and algebraic effects
- Lambda-Free Logical Frameworks