Gábor Lugosi

Gábor Lugosi

Núria Fagella
PhD in Electrical Engineering, from the Hungarian Academy of Sciences
ICREA Research Professor at Universitat Pompeu Fabra

Personal webpage

email: gabor.lugosi@upf.edu



Gábor Lugosi graduated in electrical engineering at the Technical University of Budapest in 1987, and received his Ph.D. from the Hungarian Academy of Sciences in 1991. Since 1996, he has been at the Department of Economics, Pompeu Fabra University, Barcelona. In 2006 he became an ICREA research professor.


Research Interests

  • Theory of machine learning
  • Combinatorial statistics
  • Inequalities in probability
  • Random graphs and random structures
  • Information theory


Selected publications

  • S. Boucheron, G. Lugosi, P. Massart. Concentration Inequalities: A Nonasymptotic Theory of Independence. Oxford University Press, 2013.
  • N. Cesa-Bianchi and G. Lugosi. Prediction, Learning, and Games.  Cambridge University Press, 2006.
  • N. Broutin, L. Devroye, and G. Lugosi. Almost optimal sparsification of random geometric graphs. Annals of Applied Probability, 2016.
  • C. Brownlees, E. Joly, and G. Lugosi. Empirical risk minimization for heavy-tailed losses. Annals of Statistics, 43:2507–2536, 2015.
  • J.Y. Audibert, S. Bubeck, and G. Lugosi. Regret in online combinatorial optimization. Mathematics of Operations Research, 39:31–45, 2014.