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 1109.5404stat.MLcs.AImath.STstat.TH
收藏

链图的最优学习

Towards Optimal Learning of Chain Graphs

Linköping University(林雪平大学)

Jose M. Peña

摘要:

本文将Meek猜想(Meek 1997)从有向无圈图推广到链图,并证明了推广的猜想成立。具体地说,我们证明了:如果一个链图H是由另一个链图G导出的独立模型的独立映射,那么(i)G可以通过一个有向和无向边添加以及可行的分裂和合并序列转化为H,并且(ii)在序列H中的每个操作之后,仍然是由G导出的独立模型的独立映射.我们的结果对于从数据中学习链图具有与Meek猜想的证明(Chickering 2002)对于从数据中学习贝叶斯网络具有相同的重要后果:它使得在温和的假设下开发高效且渐近正确的学习算法成为可能。

英文摘要:

In this paper, we extend Meek's conjecture (Meek 1997) from directed and acyclic graphs to chain graphs, and prove that the extended conjecture is true. Specifically, we prove that if a chain graph H is an independence map of the independence model induced by another chain graph G, then (i) G can be transformed into H by a sequence of directed and undirected edge additions and feasible splits and mergings, and (ii) after each operation in the sequence H remains an independence map of the independence model induced by G. Our result has the same important consequence for learning chain graphs from data as the proof of Meek's conjecture in (Chickering 2002) had for learning Bayesian networks from data: It makes it possible to develop efficient and asymptotically correct learning algorithms under mild assumptions.

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。

↑