Probabilistic Programming Meets Automata Theory: Exact Inference using Weighted Automata

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Geißler, Dominik, Winkler, Tobias
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918248998502400
author Geißler, Dominik
Winkler, Tobias
author_facet Geißler, Dominik
Winkler, Tobias
contents Probabilistic programs encode stochastic models as ordinary-looking programs with primitives for sampling numbers from predefined distributions and conditioning. Their applications include, among many others, machine learning and modeling of autonomous systems. The analysis of probabilistic programs is often quantitative - it involves reasoning about numerical properties like probabilities and expectations. A particularly important quantitative property of probabilistic programs is their posterior distribution, i.e., the distribution over possible outputs for a given input (or prior) distribution. Computing the posterior distribution exactly is known as exact inference. We present our current research using weighted automata, a generalization of the well-known finite automata, for performing exact inference in a restricted class of discrete probabilistic programs. This is achieved by encoding distributions over program variables - possibly with infinite support - as certain weighted automata. The semantics of our programming language then corresponds to common automata-theoretic constructions, such as product, concatenation, and others.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Probabilistic Programming Meets Automata Theory: Exact Inference using Weighted Automata
Geißler, Dominik
Winkler, Tobias
Formal Languages and Automata Theory
Programming Languages
Probabilistic programs encode stochastic models as ordinary-looking programs with primitives for sampling numbers from predefined distributions and conditioning. Their applications include, among many others, machine learning and modeling of autonomous systems. The analysis of probabilistic programs is often quantitative - it involves reasoning about numerical properties like probabilities and expectations. A particularly important quantitative property of probabilistic programs is their posterior distribution, i.e., the distribution over possible outputs for a given input (or prior) distribution. Computing the posterior distribution exactly is known as exact inference. We present our current research using weighted automata, a generalization of the well-known finite automata, for performing exact inference in a restricted class of discrete probabilistic programs. This is achieved by encoding distributions over program variables - possibly with infinite support - as certain weighted automata. The semantics of our programming language then corresponds to common automata-theoretic constructions, such as product, concatenation, and others.
title Probabilistic Programming Meets Automata Theory: Exact Inference using Weighted Automata
topic Formal Languages and Automata Theory
Programming Languages
url https://arxiv.org/abs/2512.13185