10.4230/LIPICS.ICLP.2010.74
Fierens, Daan
Daan
Fierens
Improving the Efficiency of Gibbs Sampling for Probabilistic Logical Models by Means of Program Specialization
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
2010
Article
Probabilistic logical models
probabilistic logic programming
program specialization
Gibbs sampling
Hermenegildo, Manuel
Manuel
Hermenegildo
Schaub, Torsten
Torsten
Schaub
2010
2010-06-25
2010-06-25
2010-06-25
en
urn:nbn:de:0030-drops-25857
10.4230/LIPIcs.ICLP.2010
978-3-939897-17-0
1868-8969
10.4230/LIPIcs.ICLP.2010
LIPIcs, Volume 7, ICLP 2010
Technical Communications of the 26th International Conference on Logic Programming
2013
7
11
74
83
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
Hermenegildo, Manuel
Manuel
Hermenegildo
Schaub, Torsten
Torsten
Schaub
1868-8969
Leibniz International Proceedings in Informatics (LIPIcs)
2010
7
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
10 pages
333432 bytes
application/pdf
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license
info:eu-repo/semantics/openAccess
There is currently a large interest in probabilistic logical models. A popular algorithm for approximate probabilistic inference with such models is Gibbs sampling. From a computational perspective, Gibbs sampling boils down to repeatedly executing certain queries on a knowledge base composed of a static part and a dynamic part. The larger the static part, the more redundancy there is in these repeated calls. This is problematic since inefficient Gibbs sampling yields poor approximations.
We show how to apply program specialization to make Gibbs sampling more efficient. Concretely, we develop an algorithm that specializes the definitions of the query-predicates with respect to the static part of the knowledge base. In experiments on real-world benchmarks we obtain speedups of up to an order of magnitude.
LIPIcs, Vol. 7, Technical Communications of the 26th International Conference on Logic Programming, pages 74-83