Academic Journal

On Iteration in Discrete Probabilistic Programming

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: On Iteration in Discrete Probabilistic Programming
Συγγραφείς: Torres-Ruiz, Mateo, Piedeleu, Robin, Silva, Alexandra, Zanasi, Fabio
Συνεισφορές: Mateo Torres-Ruiz and Robin Piedeleu and Alexandra Silva and Fabio Zanasi
Στοιχεία εκδότη: Schloss Dagstuhl – Leibniz-Zentrum für Informatik
Έτος έκδοσης: 2024
Συλλογή: DROPS - Dagstuhl Research Online Publication Server (Schloss Dagstuhl - Leibniz Center for Informatics )
Θεματικοί όροι: Probabilistic programming, Programming languages semantics, Unbounded iteration
Περιγραφή: Discrete probabilistic programming languages provide an expressive tool for representing and reasoning about probabilistic models. These languages typically define the semantics of a program through its posterior distribution, obtained through exact inference techniques. While the semantics of standard programming constructs in this context is well understood, there is a gap in extending these languages with tools to reason about the asymptotic behaviour of programs. In this paper, we introduce unbounded iteration in the context of a discrete probabilistic programming language, give it a semantics, and show how to compute it exactly. This allows us to express the stationary distribution of a probabilistic function while preserving the efficiency of exact inference techniques. We discuss the advantages and limitations of our approach, showcasing their practical utility by considering examples where bounded iteration poses a challenge due to the inherent difficulty of assessing the proximity of a distribution to its stationary point.
Τύπος εγγράφου: article in journal/newspaper
conference object
Περιγραφή αρχείου: application/pdf
Γλώσσα: English
Relation: Is Part Of LIPIcs, Volume 299, 9th International Conference on Formal Structures for Computation and Deduction (FSCD 2024); https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FSCD.2024.20
DOI: 10.4230/LIPIcs.FSCD.2024.20
Διαθεσιμότητα: https://doi.org/10.4230/LIPIcs.FSCD.2024.20
https://nbn-resolving.org/urn:nbn:de:0030-drops-203490
https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FSCD.2024.20
Rights: https://creativecommons.org/licenses/by/4.0/legalcode
Αριθμός Καταχώρησης: edsbas.6547585
Βάση Δεδομένων: BASE
Περιγραφή
DOI:10.4230/LIPIcs.FSCD.2024.20