The Geometry of Bayesian Programming

Ugo Dal Lago (1, 2) , Naohiko Hoshino (3)

1 DISI - Dipartimento di Scienze dell'Informazione [Bologna]
2 FOCUS - Foundations of Component-based Ubiquitous Systems
3 RIMS - Research Institute for Mathematical Sciences

We give a geometry of interaction model for a typed λ-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.

Domaines: Logique en informatique [cs.LO]

Ugo Dal Lago, Naohiko Hoshino. The Geometry of Bayesian Programming. LICS 2019 - 34th Annual ACM/IEEE Symposium on Logic in Computer Science, Jun 2019, Vancouver, Canada. pp.1-13, ⟨10.1109/LICS.2019.8785663⟩. ⟨hal-02399343⟩