The Geometry of Bayesian Programming

Abstract

We give a geometry of interaction model for a typed lambda-calculus endowed with operators for sampling from a continuous uniform distribution and soft conditioning, namely a paradigmatic calculus for higher-order Bayesian programming. The model is based on the category of measurable spaces and partial measurable functions, and is proved adequate with respect to both a distribution-based and a sampling based operational semantics.

References in corpus (3)

• A Convenient Category for Higher-Order Probability Theory
• A Domain Theory for Statistical Probabilistic Programming
• Formal verification of higher-order probabilistic programs