Detecting communities in random graphs

Abstract:
Much of our world is organized around categories or communities. These may be defined by nature, e.g., species, genes, galaxies, or by humans, e.g., society, products, knowledge. In many important cases these communities are not given to us and need to be learned based on local interactions or comparisons of the relevant entities. In mathematical terms: one has access to a graph and one wants to extract clusters of similar nodes. As with most unsupervised learning tasks, much of the challenge in community detection is to understand when and how such structures can be learned. This talk focuses on random graph models, showing how techniques ranging from statistics, information theory, discrete mathematics and computer science factor in to characterize the fundamental limits. 
Biography
Emmanuel Abbé received his Diploma from EPFL in 2003 and his Ph.D. degree from MIT in 2008. He joined Princeton University as an Assistant Professor in 2012 and became Associate Professor in 2016. He was a visiting professor at the Simons Institute, Berkeley, in 2015 and a von Neumann Fellow at the Institute for Advanced Study, Princeton, in 2017. Since 2018, he is a Professor at EPFL in the Department of Mathematics and in the School of Computer and Communication Sciences, where he holds the Chair of Mathematical Data Science.