Gábor Lugosi received his PhD from the Hungarian Academy of Sciences in 1991 in electrical engineering. Since September 1996, he has been at the Department of Economics, Pompeu Fabra University. He became ICREA Research Professor in 2006.
Research interests
Gábor Lugosi has mostly worked on the mathematics of machine learning, probability, mathematical statistics, information theory, and game theory. His research has been motivated by applications in telecommunications and computer science and also by game-theoretic learning. Recently he has mostly worked on high-dimensional problems in statistics, random graphs, "on-line" learning and sequential optimization, and inequalities in probability theory.
Selected publications
- Brownlees C, Gudmundsson GS & Lugosi G 2022, 'Community detection in partial correlation network models', Journal of Business and Economics Statistics, 40:1, 216-226.
- Addario-Berry L, Devroye L, Lugosi G & Velona V 2022, 'Broadcasting on random recursive trees', Annals of Applied Probability, 32(1):497-528.
- Lugosi G & Neu G 2022, 'Generalization bounds via convex analysis', Proceedings of Thirty Fifth Conference on Learning Theory, PMLR 178:3524-3546.
Selected research activities
Gábor Lugosi has made various research visits. He was a visiting researched at IMPA (Instituto de Matemática Pura e Aplicada) in May, he was a visiting researcher at the School of Computer Science at McGill University in September/October, and as a recipient of the Gordon Preston fellowship, he was a visiting researcher at the School of Mathematics at Monash University. He gave a graduate course on Random Structures and Combinatorial Statistics at the Bocconi Summer School in Advanced Statistics and Probability in July. He gave research seminars and colloquium talks at Monash University (twice), at the University of Ottawa, at McGill University, Duke University, Universitat Autònoma de Barcelona, and Nokia Bell Labs.