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.
Gábor Lugosi
Universitat Pompeu Fabra
Social & Behavioural Sciences
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
- C. Bordenave, G. Lugosi and N. Zhivotovskiy 2020, 'Noise sensitivity of the top eigenvector of a Wigner matrix', Probability Theory and Related Fields, 177, 1103–-1135.
- P. Bartlett, P.L. Long, G. Lugosi and A. Tsigler 2020, 'Benign overfitting in linear regression'. PNAS, volume 117, issue 48
- G. Lugosi and S. Mendelson 2020. 'Risk minimization by median-of-means tournaments.' Journal of the European Mathematical Society, 22:925–-965.
- Lugosi G, Mendelson S & Zhivotovskiy N. 2020, 'Concentration of the spectral norm of Erdös-Rényi random graphs'. Bernoulli, Vol. 26, No. 3, 2253-2274.
Selected research activities
Gábor Lugosi is the funding co-editor of the journal Mathematical Statistics and Learning, published by the European Mathematical Society.
He is associate editor of the journals Probability Theory and Related Fields, Annals of Applied Probability, Journal of Machine Learning Research, Machine Learning Journal, TEST, and ESAIM: Probability and Statistics.
He is the Principal Investigator of a Google Focused Award, a Fundación BBVA grant to Research groups on Big Data, a research group project funded by the Spanish Ministry of Science, Innovation, and Universities, and another one funded by the Catalan governmental agency AGAUR.