Gábor Lugosi

Universitat Pompeu Fabra

Social & Behavioural Sciences

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 problems in probability, mathematical statistics, the mathematics of learning theory, 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

- Bubeck S, Devroye L & Lugosi G 2017, 'Finding Adam in random growing trees', Random Structures and Algorithms, 50:158-172.  

- Devroye L, Györfi L, Lugosi G & Walk H 2017, 'On the measure of Voronoi cells', Journal of Applied Probability, 54, 394-408.

- Arias-Castro E, Lugosi G & Verzelen N 2017, 'Detecting a path of correlations in a network', ALEA, 14:33-44.

- Joly E, Lugosi G & Oliveira RI 2017, 'On the estimation of the mean of a random vector', Electronic Journal of Statistics, vol. 11, no. 1, 440-451.

- Seldin Y & Lugosi G 2017, ' An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits', JMLR Workshop and Conference Proceedings, 65 (COLT).

- Liu T, Lugosi G, Neu G & Tao D 2017, 'Algorithmic stability and hypothesis complexity', Proceedings of  the 34th International Conference on Machine Learning (ICML).