Published June 24, 2019
| Version v1
Conference paper
The Geometry of Bayesian Programming
- Creators
- Dal Lago, Ugo
- Hoshino, Naohiko
- Others:
- Dipartimento di Scienze dell'Informazione [Bologna] (DISI) ; Alma Mater Studiorum Università di Bologna [Bologna] (UNIBO)
- Foundations of Component-based Ubiquitous Systems (FOCUS) ; Inria Sophia Antipolis - Méditerranée (CRISAM) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Dipartimento di Informatica - Scienza e Ingegneria [Bologna] (DISI) ; Alma Mater Studiorum Università di Bologna [Bologna] (UNIBO)-Alma Mater Studiorum Università di Bologna [Bologna] (UNIBO)
- Research Institute for Mathematical Sciences (RIMS) ; Kyoto University [Kyoto]
Description
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.
Abstract
International audience
Additional details
- URL
- https://hal.archives-ouvertes.fr/hal-02399343
- URN
- urn:oai:HAL:hal-02399343v1
- Origin repository
- UNICA