Decomposition During Search for Propagation-Based Constraint Solvers

Simple item page
dc.creatorMann, Martin
dc.creatorTack, Guido
dc.creatorWill, Sebastian
dc.date2007-12-14
dc.date2008-06-11
dc.date.accessioned2026-07-07T09:43:29Z
dc.date.available2026-07-07T09:43:29Z
dc.descriptionWe describe decomposition during search (DDS), an integration of And/Or tree search into propagation-based constraint solvers. The presented search algorithm dynamically decomposes sub-problems of a constraint satisfaction problem into independent partial problems, avoiding redundant work. The paper discusses how DDS interacts with key features that make propagation-based solvers successful: constraint propagation, especially for global constraints, and dynamic search heuristics. We have implemented DDS for the Gecode constraint programming library. Two applications, solution counting in graph coloring and protein structure prediction, exemplify the benefits of DDS in practice.
dc.description20 pages, 9 figures, 2 tables; longer, more detailed version
dc.identifierhttps://arxiv.org/abs/0712.2389
dc.identifierhttp://arxiv.org/abs/0712.2389
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/162575
dc.subjectArtificial Intelligence
dc.titleDecomposition During Search for Propagation-Based Constraint Solvers
dc.typetext

Files

Collections

arXiv