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:6358@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20210625T143000
DTEND;TZID=Europe/Paris:20210625T153000
DTSTAMP:20241120T201411Z
URL:https://www.i2m.univ-amu.fr/evenements/learning-with-low-rank-approxim
 ations/
SUMMARY:Jérémy Cohen (IRISA\, équipe PANAMA\, CNRS\, Rennes): Learning w
 ith low-rank approximations
DESCRIPTION:Jérémy Cohen: Matrix and tensor factorizations are widespread
  techniques to blindly extract structure out of data. Research on tensor m
 ethods is rapidly growing and encompases many aspect of computer science s
 uch as high performance computing and large scale non-convex optimization.
  An important challenge is to propose or study matrix and tensor models wh
 ich are of practical interest while making efficient use of recent develop
 ements in both low-level tensor computation techniques such as tensor cont
 ractions on GPUs and large-scale non-convex optimization techniques such a
 s stochastic gradient algorithms and proximal algorithms. After introducin
 g low-rank approximation methods and depicting the current research landsc
 ape\, I will focus on two recent contributions: (i) Unsupervised music aut
 omatic segmentation using nonnegative Tucker decomposition (ii) Heuristic 
 extrapolated block-coordinate descent algorithm for tensor decompositions.
  \nThis seminar will be online\, please contact the organisers if you wish
  to attend (https://listes.math.cnrs.fr/wws/info/sem-signal-apprentissage)
 .\n
ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2
 021/04/Jeremy_Cohen.png
CATEGORIES:Séminaire,Signal et Apprentissage,Virtual event
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20210328T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR