We study the community detection problem on a Gaussian mixture model, in which (1) vertices are divided into $k\geq 2$ distinct communities that are not necessarily equally-sized; (2) the Gaussian perturbations for different entries in the observation matrix are not necessarily independent or identically distributed. We prove necessary and sufficient conditions for the exact recovery of the maximum likelihood estimation (MLE), and discuss the cases when these necessary and sufficient conditions give sharp threshold. Applications include the community detection on a graph where the Gaussian perturbations of observations on each edge is the sum of i.i.d.~Gaussian random variables on its end vertices, in which we explicitly obtain the threshold for the exact recovery of the MLE.
翻译:我们研究高斯混合模型中的社区探测问题,其中(1) 脊椎被分为不一定同等大小的2美元或2美元的独特社区;(2) 观测矩阵中不同条目的戈西亚扰动不一定独立或分布相同;我们证明准确恢复最大可能性估计(MLE)是必要和充分的条件,并讨论这些必要和充分条件能提供尖锐临界值的情况;应用包括在图表中的社区探测,其中每个边缘的观测结果的高西亚扰动是其末端脊椎上i.i.d.-Gausian随机变量的总和,我们在该图中明确获得准确恢复最低限值的临界值。