Convergence of the groups posterior distribution in latent or stochastic block models (Q2345132): Difference between revisions

The paper deals with latent block models and, particularly, with stochastic block models in order to facilitate the clustering analysis. The authors focus on a procedure able to cluster both objects and variables (i.e., to simultaneously cluster rows and columns of a data matrix). They propose a unified framework to establish sufficient conditions for the convergence of the groups posterior distribution to a Dirac mass located at the actual random groups configuration.