arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1507.08685cs.ITcond-mat.stat-mechmath.ITmath.STstat.TH
收藏

两组随机区组模型的渐近互信息

Asymptotic Mutual Information for the Two-Groups Stochastic Block Model

Yash Deshpande, Emmanuel Abbe, Andrea Montanari

摘要:

我们开发了一个随机块模型,一个流行的统计模型的复杂网络的大规模结构的信息论的观点。从这样的模型生成的图$G$首先从有限字母表中随机分配顶点标签,然后根据端点的标签用边概率连接顶点。在对称两群模型的情况下,我们建立了一个明确的“单字母”的表征每顶点之间的互信息的顶点标签和图。互信息的明确表达是密切相关的估计理论量,并-特别是-揭示了一个相变的临界点社区发现。在临界点以下,每顶点互信息渐近地相同,就好像边是独立的一样。相应地,没有算法比随机猜测更好地估计分区。相反,在阈值以上,每顶点互信息严格小于独立边上界。在这种情况下,存在一个程序,估计顶点标签比随机猜测。

英文摘要:

We develop an information-theoretic view of the stochastic block model, a popular statistical model for the large-scale structure of complex networks. A graph $G$ from such a model is generated by first assigning vertex labels at random from a finite alphabet, and then connecting vertices with edge probabilities depending on the labels of the endpoints. In the case of the symmetric two-group model, we establish an explicit `single-letter' characterization of the per-vertex mutual information between the vertex labels and the graph. The explicit expression of the mutual information is intimately related to estimation-theoretic quantities, and --in particular-- reveals a phase transition at the critical point for community detection. Below the critical point the per-vertex mutual information is asymptotically the same as if edges were independent. Correspondingly, no algorithm can estimate the partition better than random guessing. Conversely, above the threshold, the per-vertex mutual information is strictly smaller than the independent-edges upper bound. In this regime there exists a procedure that estimates the vertex labels better than random guessing.

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。

↑