利用不可靠Oracle学习贝叶斯和马尔可夫网络
Learning Bayesian and Markov Networks with an Unreliable Oracle
AI总结:
本文研究了在存在不可靠Oracle的情况下,马尔可夫网络和贝叶斯网络的结构学习问题,证明了在特定条件下结构的唯一可确定性,并提出了相应的学习算法。
摘要:
我们研究了在存在一个可能最多产生有限数量错误的不可靠条件独立Oracle的情况下,马尔可夫网络和贝叶斯网络的约束基于结构学习。对于马尔可夫网络,我们观察到,如果最大顶点数的不相交路径数较低,则即使错误数量是顶点数的(适度)指数级,结构仍然可以唯一确定。然而,对于贝叶斯网络,我们证明即使许多常用的图参数如树宽被限制,也不能容忍任何错误以始终确定结构。最后,我们给出了当结构唯一可确定时的结构学习算法。
英文摘要:
We study constraint-based structure learning of Markov networks and Bayesian networks in the presence of an unreliable conditional independence oracle that makes at most a bounded number of errors. For Markov networks, we observe that a low maximum number of vertex-wise disjoint paths implies that the structure is uniquely identifiable even if the number of errors is (moderately) exponential in the number of vertices. For Bayesian networks, however, we prove that one cannot tolerate any errors to always identify the structure even when many commonly used graph parameters like treewidth are bounded. Finally, we give algorithms for structure learning when the structure is uniquely identifiable.
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。