We announce the following webinar from the Statistics Series at Università Bocconi:

Date: Thursday, June 3rd, h17:00 (Italy time)
Speaker: Stanislav Volgushev (University of Toronto)  
Title: Structure learning for Extremes

Abstract: Extremal graphical models are sparse statistical models for multivariate extreme events. The underlying graph encodes conditional independencies and enables a visual interpretation of the complex extremal dependence structure. For the important case of tree models, we provide a data-driven methodology for learning the graphical structure. We show that sample versions of the extremal correlation and a new summary statistic, which we call the extremal variogram, can be used as weights for a minimum spanning tree to consistently recover the true underlying tree. Remarkably, this implies that extremal tree models can be learned in a completely non-parametric fashion by using simple summary statistics and without the need to assume discrete distributions, existence of densities, or parametric models for marginal or bivariate distributions. Extensions to more general graphs are also discussed.

The webinar will be on zoom at:
Meeting ID: 979 4263 2075
Passcode: 627490