Gabor Lugosi (Univ. Pompeu Fabra, Spain)

2023 Lorne Campbell Lecture Series

Friday, November 24th, 2023

Time: 5:30 p.m.  Place: Jeffery Hall, Room 127

Speaker: Prof. Gabor Lugosi (Univ. Pompeu Fabra, Spain)

Title: Mathematical Models of Network Archaeology

Abstract: Large networks that change dynamically over time are ubiquitous in various areas such as social networks, and epidemiology. These networks are often modeled by random dynamics which, despite being relatively simple, give a quite accurate macroscopic description of real networks. In \network archaeology" one studies statistical problems of inferring the past properties of such growing networks, given the current state of the network. In this talk, we discuss some simple network models and review recent results on revealing the past of the networks.

Bio: Professor Gabor Lugosi received the PhD degree in electrical engineering from the Hungarian Academy of Sciences. He is an ICREA (Catalan Institution for Research and Advanced Studies) Research Professor at the Department of Economics, Pompeu Fabra University, Barcelona, Spain. His main research interests include statistical learning theory, sequential prediction, nonparametric classication and regression, random graphs, and concentration inequalities.

Professor Lugosi has published over 120 papers and four research monographs, including Prediction, Learning, and Games in 2006 and Concentration Inequalities: A Nonasymptotic Theory of Independence in 2013. He has served on the editorial board of several journals including the Annals of Applied Probability, the Journal of Machine Learning Research and the IEEE Transactions on Information Theory. He has been \Medallion Lecturer" (2009) and \Blackwell Lecturer" (2021) of the Institute of Mathematical Statistics. He was an invited speaker at the 2022 International Congress of Mathematicians, and he delivered the \Breiman Lecture" in 2021 at NeurIPS, the prime conference on Machine Learning.