arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.01423cs.AI
收藏

基于不可满足核分析的命题限定中的模型枚举

Model enumeration in propositional circumscription via unsatisfiable core analysis

University of Calabria(卡拉布里亚大学)

Mario Alviano

摘要:

许多实际问题的特征在于对容许解的偏好关系,其中偏好解在某种意义下是最小的。例如,优选的诊断通常包括足以引起所观察到的异常的最小原因集合。或者,最小校正子集包括其删除足以消除所观察到的异常的最小原因集合。限制形式化的偏好关系相关联的命题理论与最小的模型。由此产生的枚举问题是解决这里通过一个新的算法,利用不可满足的核心分析。该算法的效率的经验证据是通过比较所得到的求解器,CIRCULANTINO,与HCLASP,CAMUS MCS,LBX和MCSLS的枚举的最小模型的实际应用中产生的问题的性能。本文件正在考虑被TPLP接受。

英文摘要:

Many practical problems are characterized by a preference relation over admissible solutions, where preferred solutions are minimal in some sense. For example, a preferred diagnosis usually comprises a minimal set of reasons that is sufficient to cause the observed anomaly. Alternatively, a minimal correction subset comprises a minimal set of reasons whose deletion is sufficient to eliminate the observed anomaly. Circumscription formalizes such preference relations by associating propositional theories with minimal models. The resulting enumeration problem is addressed here by means of a new algorithm taking advantage of unsatisfiable core analysis. Empirical evidence of the efficiency of the algorithm is given by comparing the performance of the resulting solver, CIRCUMSCRIPTINO, with HCLASP, CAMUS MCS, LBX and MCSLS on the enumeration of minimal models for problems originating from practical applications. This paper is under consideration for acceptance in TPLP.

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。

↑