June 12th14:30 (Shannon amphitheatre, building 660) (see location):
Romain Couillet (Centrale-Supélec)
Title: A Random Matrix Framework for BigData Machine Learning
Abstract:The recent interest for automating classification, clustering, detection, estimation of the massively large and heterogeneous data made available by modern computer and communication technologies, and the fast deployment of deep learning approaches, has spurred a new need for mathematical tools to apprehend bigdata machine learning. In this talk, I will argue that random matrix theory (RMT) is a key enabler to meet this challenge. After a brief introduction of the basic concepts, I will show how RMT helps understand and improve spectral clustering methods, semi-supervised learning and basic neural networks.
Contact: guillaume.charpiat at inria.fr