BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//6.4.7.2//EN TZID:Europe/Paris X-WR-TIMEZONE:Europe/Paris BEGIN:VEVENT UID:1-448@lptms.universite-paris-saclay.fr DTSTART:20160906T140000Z DTEND:20160906T163000Z DTSTAMP:20160727T102822Z URL:http://www.lptms.universite-paris-saclay.fr/seminars/soutenance-de-the se-joel-bun/ SUMMARY:Soutenance de thèse: Joël Bun - IPN-batiment 100\, Auditoriurm - 6 Sep 16 14:00 DESCRIPTION:\n \;\nApplications of Random Matrix Theory for high-dimens ional statistics.\n \;\nIn the present era of Big Data\, new statistic al methods are needed to decipher large dimensional data sets that are no w routinely generated in almost all fields – physics\, image analysis\, genomics\, epidemiology\, engineering and finance\, to quote only a few. I t is very natural to try to identify common causes that explain the joint dynamics of a large number of quantities. The primary aim of this thesis is to understand theoretically the so-called curse of dimensionality that describe phenomena which arise in high-dimensional space using Random Matr ix Theory. Special care is devoted to the statistics of the eigenvectors o f large noisy matrices\, which turn out to be crucial for many application s. Moreover\, I will present how to build reliable estimators that are con sistent with the dimension of the problem. In the case of correlation matr ices\, the estimator we obtain provide better performance than all previou sly proposed methods for real-world applications within financial markets. CATEGORIES:seminars LOCATION:IPN-batiment 100\, Auditoriurm\, 15 Rue Georges Clemenceau\, orsay \, France GEO:48.698196;2.181773 X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=15 Rue Georges Clemenceau\, orsay\, France;X-APPLE-RADIUS=100;X-TITLE=IPN-batiment 100\, Auditoriurm: geo:48.698196,2.181773 END:VEVENT END:VCALENDAR