Pré-Publication, Document De Travail Année : 2023

Verifying Performance Properties of Probabilistic Inference

Résumé

In this extended abstract, we discuss the opportunity to formally verify that inference systems for probabilistic programming guarantee good performance. In particular, we focus on hybrid inference systems that combine exact and approximate inference to try to exploit the advantages of each. Their performance depends critically on a) the division between exact and approximate inference, and b) the computational resources consumed by exact inference. We describe several projects in this direction. Semi-symbolic Inference (SSI) is a type of hybrid inference system that provides limited guarantees by construction on the exact/approximate division. In addition to these limited guarantees, we also describe ongoing work to extend guarantees to a more complex class of programs, requiring a program analysis to ensure the guarantees. Finally, we also describe work on verifying that inference systems using delayed sampling -- another type of hybrid inference -- execute in bounded memory. Together, these projects show that verification can deliver the performance guarantees that probabilistic programming languages need.

Fichier principal
Vignette du fichier
2307.07355.pdf (88.66 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04488233 , version 1 (04-03-2024)

Licence

Identifiants

Citer

Eric Atkinson, Ellie Y. Cheng, Guillaume Baudart, Louis Mandel, Michael Carbin. Verifying Performance Properties of Probabilistic Inference. 2024. ⟨hal-04488233⟩
150 Consultations
156 Téléchargements

Altmetric

Partager

  • More