Bayesian Networks and Proof-Nets: a proof-theoretical account of Bayesian Inference

Abstract

We uncover a strong correspondence between Bayesian Networks and (Multiplicative) Linear Logic Proof-Nets, relating the two as a representation of a joint probability distribution and at the level of computation, so yielding a proof-theoretical account of Bayesian Inference.

Presented at the Workshop "Logic of Probabilistic Programming" (CIRM Marseille, 31 Jan- 4 Feb 2022): \url{https://conferences.cirm-math.fr/2507.html}