Publication
Exploiting Causal Independence Using Weighted Model Counting
AbstractPrevious studies have demonstrated that encoding a Bayesian network into a SAT-CNF formula and then performing weighted model counting using a backtracking search algorithm can be an effective method for exact inference in Bayesian networks. In this paper, we present techniques for improving this approach for Bayesian networks with noisy-OR and noisy-MAX relations—two relations which are widely used in practice as they can dramatically reduce thenumber of probabilities one needs to specify. In particular, we present two space efficient CNF encodings for noisy-OR/MAX and explore alternative search ordering heuristics. We experimentally evaluated our techniques on large-scale real and randomly generated Bayesian networks. On these benchmarks, our techniques gave speedups of up to two ordersof magnitude over the best previous approaches and scaled up to networks with larger numbers of random variables.
Download publicationRelated Resources
See what’s new.
2024
GraphSeam: Supervised Graph Learning Framework for Semantic UV MappingProposing a fully automated UV mapping framework that enables users to…
2007
Perturbative solutions of the extended Einstein constraint equationsThe extended constraint equations arise as a special case of the…
2018
HydroRing: Supporting Mixed Reality Haptics Using Liquid FlowCurrent haptic devices are often bulky and rigid, making them…
2007
Position Statement: Design Studio Culture in HCIIn defining a virtual design studio culture (from now I will call it a…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us