The Geometry of Bayesian Programming
Programming Languages
2023-06-22 v1
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.
Cite
@article{arxiv.1904.07425,
title = {The Geometry of Bayesian Programming},
author = {Ugo Dal Lago and Naohiko Hoshino},
journal= {arXiv preprint arXiv:1904.07425},
year = {2023}
}