Random Matrices in Machine Learning

Jeudi 16 juin 2016 14:00-15:00 - Romain Couillet - Centrale Supélec

Résumé : Thanks to its efficiently exploiting degrees of freedom in large multi-dimensional problems, random matrix theory has today become a compelling field in modern (multi-antenna multi-user multi-cell) wireless communications and is currently making powerful headway into large dimensional signal processing and statistics. With the advent of the big data paradigm, challenging machine learning questions arise, which we claim random matrix theory can address like no other tool before.
In this talk, after a basic introduction and motivation to random matrix theory, we shall discuss our early findings in the theoretical understanding and the resulting practical improvements of kernel spectral clustering for large dimensional data, community detection on large realistic graphs, and shall also briefly discuss neural networks, robust estimation, etc.
Bio : Romain Couillet received his MSc in Mobile Communications at the Eurecom Institute and his MSc in Communication Systems in Telecom ParisTech, France in 2007. From 2007 to 2010, he worked with ST-Ericsson as an Algorithm Development Engineer on the Long Term Evolution Advanced project, where he prepared his PhD with Supelec, France, which he graduated in November 2010. He is currently an assistant professor in the Telecommunication department of CentraleSupélec, France. His research topics are in random matrix theory applied to statistics, signal processing, machine learning, and wireless communications. 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), of the 2011 EEA/GdR ISIS/GRETSI best PhD thesis award, and of the Valuetools 2008 best student paper award.
Related references :
* R. Couillet, F. Benaych-Georges, « Kernel Spectral Clustering of Large Dimensional Data », (submitted to) Electronic Journal of Statistics, 2015.
* H. Tiomoko Ali, R. Couillet, « Performance analysis of spectral community detection in realistic graph models », IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’16), Shangai, China, 2016.
* R. Couillet, G. Wainrib, H. Sevi, H. Tiomoko Ali, « The asymptotic performance of linear echo state neural networks », (submitted to) Journal of Machine Learning Research, 2016.
* R. Couillet, F. Pascal, J. W. Silverstein, « The Random Matrix Regime of Maronna’s M-estimator with elliptically distributed samples », Elsevier Journal of Multivariate Analysis, vol. 139, pp. 56-78, 2015.
* R. Couillet, M. McKay, « Large Dimensional Analysis and Optimization of Robust Shrinkage Covariance Matrix Estimators », Elsevier Journal of Multivariate Analysis, vol. 131, pp. 99-120, 2014.

Lieu : Salle 117-119

Random Matrices in Machine Learning  Version PDF