Can random matrices change the future of machine learning?


Séminaire Données et Aléatoire Théorie & Applications

16/01/2020 - 14:00 Mr Romain COUILLET (CentraleSupélec, University ParisSaclay, IDEX GSTATS Chair & MIAI LargeDATA Chair, University Grenoble-Alpes) Salle 106 - Batiment IMAG

Many standard machine learning algorithms and intuitions are known to misbehave, if not dramatically collapse, when operated on large dimensional data. In this talk, we will show that large dimensional statistics, and particularly random matrix theory, not only can elucidate this behavior but provides a new set of tools to understand and (sometimes drastically) improve machine learning algorithms. Besides, we will show that our various theoretical findings are provably applicable to very realistic and not-so-large dimensional data.

Bio: Romain Couillet is a full professor in the LSS laboratory at CentraleSupélec, University of ParisSaclay France, and the holder of the UGA IDEX GSTATS DataScience Chair at GIPSA-lab & MIAI LargeDATA Chair, at University of Grenoble-Alpes, France. His research topics are in random matrix theory applied to statistics, machine learning, and signal processing. He is an IEEE Senior Member. In 2015, he received the HDR title from University ParisSud. He is the recipient of the 2013 CNRS Bronze Medal in the section "science of information and its interactions", of the 2013 IEEE ComSoc Outstanding Young Researcher Award (EMEA Region), and of the 2011 EEA/GdR ISIS/GRETSI best PhD thesis award.