In this talk I discuss mean estimation based on independent observations, perhaps the most basic problems in statistics. Despite its long history, the subject has attracted a flurry of renewed activity. Motivated by applications in machine learning and data science, the problem has been viewed from new angles both from statistical and computational points of view. We review some recent results on the statistical performance of mean estimators that allow heavy tails and adversarial contamination in the data, focusing on high-dimensional aspects.
Gabor Lugosi (Pompeu Fabra University, Barcelona)
Gabor Lugosi is an ICREA research professor at the Department of Economics and Business, Pompeu Fabra University, Barcelona. He received his Ph.D. from the Hungarian Academy of Sciences in 1991. His research has mostly focused on the mathematical aspects of machine learning and related topics in probability and mathematical statistics, including combinatorial statistics, the analysis of random structures, and information theory. He is a co-author of several monographs on pattern recognition, density estimation, online learning, and concentration inequalities.
More from the Same Authors
2017 Poster: Boltzmann Exploration Done Right »
Nicolò Cesa-Bianchi · Claudio Gentile · Gergely Neu · Gabor Lugosi
2012 Workshop: Multi-Trade-offs in Machine Learning »
Yevgeny Seldin · Guy Lever · John Shawe-Taylor · Nicolò Cesa-Bianchi · Yacov Crammer · Francois Laviolette · Gabor Lugosi · Peter Bartlett
2012 Poster: Mirror Descent Meets Fixed Share (and feels no regret) »
Nicolò Cesa-Bianchi · Pierre Gaillard · Gabor Lugosi · Gilles Stoltz