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
- Lugosi G, Pike-Burke C& Savalle PA 2023, 'Bandit problems with fidelity rewards', Journal of machine learning research, (328):1−44, 2023.
- Briend S, Cavillo F & Lugosi G 2023, 'Archaeology of random recursive dags and Cooper-Frieze random networks', Combinatorics, Probability and Computing, 32:6, 859-873, 2023.
- Khaleghi A & Lugosi G 2023, 'Inferring the mixing properties of a stationary ergodic process from a single path', IEEE Transactions on Information Theory, 69:6, 4014-4026.
Selected research activities
Gábor Lugosi is co-editor of the journal Mathematical Statistics and Learning and associate editor of the journals Electronic Journal of Probability, Electronic Communications of Probability, Probability Theory and Related Fields, Journal of Machine Learning Research, TEST, ESAIM: Probability and Statistics.
In 2023 he was elected to be a member of the Institute of Mathematical Statistics Council.
He was plenary lecturer at the IMS International Conference on Statistics and Data Science and he gave invited talks at Queens University, where he gave the Lorne Campbell Colloquium, University of Vienna, IMPA (Rio de Janeiro), University of Toronto, Mohamed bin Zayed University of Artificial Intelligence, University of Copenhagen, and University of Zagreb.