BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:1908@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20170929T140000
DTEND;TZID=Europe/Paris:20170929T150000
DTSTAMP:20170914T120000Z
URL:https://www.i2m.univ-amu.fr/evenements/a-random-matrix-framework-for-b
 ig-data-machine-learning/
SUMMARY: (...): A random matrix framework for big data machine learning
DESCRIPTION:: Thanks to its efficiently exploiting degrees of freedom in la
 rge multi-dimensional problems\, random matrix theory has today become a c
 ompelling field in modern (multi-antenna multi-user multi-cell) wireless c
 ommunications and is currently making powerful headway into large dimensio
 nal signal processing and statistics. With the advent of the big data para
 digm\, challenging machine learning questions arise\, which we claim rando
 m matrix theory can address like no other tool before.In this talk\, after
  a basic introduction and motivation to random matrix theory\, we shall di
 scuss our early findings in the theoretical understanding and the resultin
 g practical improvements of kernel spectral clustering and semi-supervised
  learning for large dimensional data\, community detection on large realis
 tic graphs\, and shall also briefly discuss neural networks as well as rob
 ust statistics applications. http://romaincouillet.hebfree.org
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20170326T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR