Reconstruction on the stochastic block model

Abstract: The problem of community detection is one of great relevance in machine learning and data science. The goal is to group vertices that behave similarly within a graph or network. In the context of this problem, the Stochastic Block Model is one of the most well-studied random graph models. In this talk, we discuss reconstruction results for this model, highlighting a provably optimal algorithm that is closely related to belief propagation.

Computer scienceMathematicsPhysics

Audience: researchers in the topic

MIT Simple Person's Applied Mathematics Seminar