Two-sample test of stochastic block models
针对具有社区结构的大规模网络，提出基于邻接矩阵差异最大条目的检验统计量，推导其渐近零分布并证明渐近功效，模拟和真实数据表现良好。
In this paper, we consider the problem of two-sample test of large networks with community structures. A test statistic is proposed based on the maximum entry of the difference between the two adjacency matrices. Asymptotic null distribution is derived, and the asymptotic power guarantee against the alternative hypothesis is provided. The simulations and real data examples show that the proposed test statistic performs well.