arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1206.3265cs.AI
收藏

灵敏度分析与参数整定的计算复杂性

The Computational Complexity of Sensitivity Analysis and Parameter Tuning

University of Utrecht(乌得勒支大学)

Johan Kwisthout, Linda C. van der Gaag

摘要:

虽然已知的概率网络中的灵敏度分析和参数调整算法的运行时间与网络的大小成指数关系,但这些问题的精确计算复杂性尚未建立。在本文中,我们研究了几个变种的调谐问题,并表明这些问题是NPPP-完全的一般。我们进一步表明,问题仍然是NP-完全或PP-完全的,一些限制性的变种。这些复杂性的结果提供了洞察力,在灵敏度分析和调整的最新成果是否可以扩展到更一般的,实用的方法。

英文摘要:

While known algorithms for sensitivity analysis and parameter tuning in probabilistic networks have a running time that is exponential in the size of the network, the exact computational complexity of these problems has not been established as yet. In this paper we study several variants of the tuning problem and show that these problems are NPPP-complete in general. We further show that the problems remain NP-complete or PP-complete, for a number of restricted variants. These complexity results provide insight in whether or not recent achievements in sensitivity analysis and tuning can be extended to more general, practicable methods.

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。

↑