arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.02209cs.MAcs.AI
收藏

用抽取法改进极大和法求解多环分布约束优化问题

Improving Max-Sum through Decimation to Solve Loopy Distributed Constraint Optimization Problems

IIIA-CSIC(西班牙国家研究委员会人工智能研究所);Université de Lyon(里昂大学);MINES Saint-Etienne(圣埃蒂安国立矿业学校)

Jesús Cerquides, Rémi Emonet, Gauthier Picard, Juan A. Rodríguez-Aguilar

摘要:

在求解大型分布式约束优化问题(DCOP)的背景下,置信传播和近似推理算法的选择。然而,一般来说,当因子图是非常循环的(即循环的)时,这些求解方法由于不收敛和许多交换的消息而性能不佳。为了提高Max-Sum推理算法在求解循环约束优化问题时的性能,本文借鉴了用于求解稀疏随机图(k-可满足性)的置信传播引导抽取算法.我们提出了新的DeciMaxSum方法,它是参数化的政策,以决定何时触发抽取,抽取哪些变量,以及哪些值分配给抽取变量。基于一个经典的BP基准(伊辛模型)的实证评估,这些组合的政策表现出更好的性能比国家的最先进的竞争对手。

英文摘要:

In the context of solving large distributed constraint optimization problems (DCOP), belief-propagation and approximate inference algorithms are candidates of choice. However, in general, when the factor graph is very loopy (i.e. cyclic), these solution methods suffer from bad performance, due to non-convergence and many exchanged messages. As to improve performances of the Max-Sum inference algorithm when solving loopy constraint optimization problems, we propose here to take inspiration from the belief-propagation-guided dec-imation used to solve sparse random graphs (k-satisfiability). We propose the novel DeciMaxSum method, which is parameterized in terms of policies to decide when to trigger decimation, which variables to decimate, and which values to assign to decimated variables. Based on an empirical evaluation on a classical BP benchmark (the Ising model), some of these combinations of policies exhibit better performance than state-of-the-art competitors.

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。

↑