DeLTA seminar by Gábor Lugosi

Delta logo

Zoom link


Gábor Lugosi, Pompeu Fabra University

Portrait of Gabor Lugosi


Learning the structure of graphical models by covariance queries


The dependence structure of high-dimensional distributions is oftenmodeled by graphical models. The problem of learning the graphunderlying such distributions has received a lot of attention instatistics and machine learning. In problems of very high dimension,it is often too costly even to store the sample covariance matrix. Wepropose a new model in which one can query single entries of thecovariance matrix. We construct computationally efficient algorithmsfor structure recovery in Gaussian graphical models with computationalcomplexity that is quasi-linear in the dimension. We presentalgorithms that work for trees and, more generally, for graphs ofsmall treewidth. The talk is based on joint  work with JakubTruszkowski, Vasiliki Velona, and Piotr Zwiernik.


You can subscribe to the DeLTA Seminar mailing list by sending an empty email to
Online calendar
DeLTA Lab page