Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Torres-Ruiz, Mateo, Piedeleu, Robin, Silva, Alexandra, Zanasi, Fabio
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.04649
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918154848960512
author Torres-Ruiz, Mateo
Piedeleu, Robin
Silva, Alexandra
Zanasi, Fabio
author_facet Torres-Ruiz, Mateo
Piedeleu, Robin
Silva, Alexandra
Zanasi, Fabio
contents We extend the synthetic theories of discrete and Gaussian categorical probability by introducing a diagrammatic calculus for reasoning about hybrid probabilistic models in which continuous random variables, conditioned on discrete ones, follow a multivariate Gaussian distribution. This setting includes important classes of models such as Gaussian mixture models, where each Gaussian component is selected according to a discrete variable. We develop a string diagrammatic syntax for expressing and combining these models, give it a compositional semantics, and equip it with a sound and complete equational theory that characterises when two models represent the same distribution.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Complete Diagrammatic Calculus for Conditional Gaussian Mixtures
Torres-Ruiz, Mateo
Piedeleu, Robin
Silva, Alexandra
Zanasi, Fabio
Logic in Computer Science
We extend the synthetic theories of discrete and Gaussian categorical probability by introducing a diagrammatic calculus for reasoning about hybrid probabilistic models in which continuous random variables, conditioned on discrete ones, follow a multivariate Gaussian distribution. This setting includes important classes of models such as Gaussian mixture models, where each Gaussian component is selected according to a discrete variable. We develop a string diagrammatic syntax for expressing and combining these models, give it a compositional semantics, and equip it with a sound and complete equational theory that characterises when two models represent the same distribution.
title A Complete Diagrammatic Calculus for Conditional Gaussian Mixtures
topic Logic in Computer Science
url https://arxiv.org/abs/2510.04649