Conditioned Belief Propagation revisited (extended version)

Veröffentlichung
2014-08-11Authors
Geier, Thomas
Richter, Felix
Biundo, Susanne
Bericht
Faculties
Fakultät für Ingenieurwissenschaften und InformatikSeries
Ulmer Informatik-Berichte
Abstract
Belief Propagation (BP) applied to cyclic problems is a well known approximate inference scheme for probabilistic graphical models. To improve its accuracy, Conditioned Belief Propagation (CBP) has been proposed, which splits a problem into subproblems by conditioning on variables, applies BP to subproblems, and merges the results to produce an answer to the original problem. In this work, we propose a reformulated version of CBP that exhibits anytime behavior and allows for more specific tuning by formalizing a further aspect of the algorithm through the use of a leaf selection heuristic. We propose several simple and easy to compute heuristics and demonstrate their performance using an empirical evaluation on randomly generated problems.
Date created
2014
Subject headings
[GND]: Markov-Zufallsfeld[LCSH]: Artificial intelligence | Conditioning
[Free subject headings]: Belief propagation | Markov networks | Probabilistic inference
[DDC subject group]: DDC 004 / Data processing & computer science
Metadata
Show full item recordDOI & citation
Please use this identifier to cite or link to this item: http://dx.doi.org/10.18725/OPARU-3199
Geier, Thomas; Richter, Felix; Biundo, Susanne (2014): Conditioned Belief Propagation revisited (extended version). Open Access Repositorium der Universität Ulm und Technischen Hochschule Ulm. http://dx.doi.org/10.18725/OPARU-3199
Citation formatter >