Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Fast parallel constraint satisfaction
Artificial Intelligence
Tractable constraints on ordered domains
Artificial Intelligence
Belief Optimization for Binary Networks: A Stable Alternative to Loopy Belief Propagation
UAI '01 Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence
Directed constraint networks: a relational framework for causal modeling
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Iterative join-graph propagation
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Turbo decoding as an instance of Pearl's “belief propagation” algorithm
IEEE Journal on Selected Areas in Communications
Using expectation maximization to find likely assignments for solving CSP's
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Join-graph propagation algorithms
Journal of Artificial Intelligence Research
SampleSearch: Importance sampling in presence of determinism
Artificial Intelligence
Characterizing propagation methods for boolean satisfiability
SAT'06 Proceedings of the 9th international conference on Theory and Applications of Satisfiability Testing
| Hi-index | 0.00 |
In non-ergodic belief networks the posterior belief of many queries given evidence may become zero. The paper shows that when belief propagation is applied iteratively over arbitrary networks (the so called, iterative or loopy belief propagation (IBP)) it is identical to an arc-consistency algorithm relative to zero-belief queries (namely assessing zero posterior probabilities). This implies that zero-belief conclusions derived by belief propagation converge and are sound. More importantly, it suggests that the inference power of IBP is as strong and as weak as that of arcconsistency. This allows the synthesis of belief networks for which belief propagation is useless on one hand, and focuses the investigation on classes of belief networks for which belief propagation may be zero-complete. Finally, we show empirically that IBP's accuracy is correlated with extreme probabilities, therefore explaining its success over coding applications.