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:6558@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20210129T143000
DTEND;TZID=Europe/Paris:20210129T153000
DTSTAMP:20241120T201739Z
URL:https://www.i2m.univ-amu.fr/evenements/tensor-networks-for-machine-lea
 rning-guillaume-rabusseau/
SUMMARY:Guillaume Rabusseau (Université de Montréal): Tensor networks for
  machine learning - Guillaume Rabusseau
DESCRIPTION:Guillaume Rabusseau: In this talk\, I will give an introduction
  to tensor networks and give a very brief overview of three recent contrib
 utions from my group aiming at going beyond classical tensor decomposition
  models using the tensor network formalism.\nTensors are high order genera
 lization of vectors and matrices. Similar to matrix factorization techniqu
 es\, one of the goal of tensor decomposition techniques is to express a te
 nsor as a product of small factors\, thus reducing the number of parameter
 s and potentially regularizing machine learning models. While linear algeb
 ra is ubiquitous and taught in most undergrad curriculum\, tensor and mult
 ilinear algebra can be daunting. In the first part of the talk\, I will tr
 y to give an easy and accessible introduction to tensor methods using the 
 tensor network formalism. Tensor networks are an intuitive diagrammatic no
 tation allowing one to easily reason about complex operations on high-orde
 r tensors.\nIn the second part of the talk\, I will very briefly give an o
 verview of three recent work from my group\, ranging from tensorizing rand
 om projections to studying the VC dimension of tensor network models.\nBIO
 \nGuillaume Rabusseau is an assistant professor at Univeristé de Montréa
 l and holds a Canada CIFAR AI chair at the Mila research institute. Prior 
 to joining Mila\, he was an IVADO postdoctoral research fellow in the Reas
 oning and Learning Lab at McGill University\, where he worked with Prakash
  Panangaden\, Joelle Pineau and Doina Precup. He obtained his PhD in compu
 ter science in 2016 at Aix-Marseille University under the supervision of F
 rançois Denis and Hachem Kadri. His research interests lie at the interse
 ction of theoretical computer science and machine learning\, and his work 
 revolves around exploring inter-connections between tensors and machine le
 arning to develop efficient learning methods for structured data relying o
 n linear and multilinear algebra.\nVisio: https://univ-amu-fr.zoom.us/j/97
 958103420?pwd=MXJIMEsrSTlvNnl6czNQcGFESkYwdz09
ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2
 020/01/Guillaume_Rabusseau.jpg
CATEGORIES:Séminaire,Signal et Apprentissage,Virtual event
LOCATION:I2M Chateau-Gombert - CMI\, Salle de Séminaire R164 (1er étage)\
 , 39 Rue Joliot Curie\, 13013 Marseille\, France\, Campus Château-Gombert
 \, 
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=39 Rue Joliot Curie\, 13013
  Marseille\, France\, Campus Château-Gombert\, ;X-APPLE-RADIUS=100;X-TITL
 E=I2M Chateau-Gombert - CMI\, Salle de Séminaire R164 (1er étage):geo:0,
 0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20201025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR