arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0712.2389cs.AI
收藏

基于分解的约束求解器搜索过程中的分解

Decomposition During Search for Propagation-Based Constraint Solvers

Albert-Ludwigs-University Freiburg(弗莱堡阿尔伯特-路德维希大学);Saarland University(萨尔大学)

Martin Mann, Guido Tack, Sebastian Will

摘要:

我们描述了分解过程中的搜索(DDS),与/或树搜索到基于传播的约束求解器的集成。该搜索算法将约束满足问题的子问题动态分解为独立的部分问题,避免了冗余工作。本文讨论了DDS如何与使基于传播的求解器成功的关键功能相互作用:约束传播,特别是对于全局约束,以及动态搜索算法。我们已经实现了DDS的Gecode约束编程库。两个应用,解决方案计数在图着色和蛋白质结构预测,体现了DDS在实践中的好处。

英文摘要:

We 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑