Pointless learning

Abstract : Bayesian inversion is at the heart of probabilistic programming and more generally machine learning. Understanding inversion is made difficult by the pointful (kernel-centric) point of view usually taken in the literature. We develop a pointless (kernel-free) approach to inversion. While doing so, we revisit some foundational objects of probability theory, unravel their category-theoretical underpinnings and show how pointless Bayesian inversion sits naturally at the centre of this construction .
Type de document :
Pré-publication, Document de travail
Accepted to the 20th International Conference on Foundations of Software Science and Computation .. 2017
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01429663
Contributeur : Ilias Garnier <>
Soumis le : lundi 9 janvier 2017 - 09:22:49
Dernière modification le : jeudi 26 octobre 2017 - 16:34:02
Document(s) archivé(s) le : lundi 10 avril 2017 - 12:59:47

Fichier

fossacs2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01429663, version 1

Citation

Florence Clerc, Vincent Danos, Fredrik Dahlqvist, Ilias Garnier. Pointless learning. Accepted to the 20th International Conference on Foundations of Software Science and Computation .. 2017. 〈hal-01429663v1〉

Partager

Métriques

Consultations de la notice

25

Téléchargements de fichiers

29