The Statistical Seminar: Every Monday at 2:00 pm.

Time: 2:00 pm – 3:15 pm
Date: February 11,  2019
Place: Room 3001

Olga KLOPP (CREST and ESSEC) – “Graphon Estimation in cut distance”
Abstract:
We consider the twin problems of estimating the connection probability matrix of an inhomogeneous random graph and the graphon of a W-random graph. We establish the minimax estimation rates with respect to the cut metric for classes of block constant matrices and step function graphons. Surprisingly, our results imply that, from the minimax point of view, the raw data, that is, the adjacency matrix of the observed graph, is already optimal and more involved procedures cannot improve the convergence rates for this metric. This phenomenon contrasts with optimal rates of convergence with respect to other classical distances for graphons.