BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.4.6.4.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:6687@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20210129T143000
DTEND;TZID=Europe/Paris:20210129T153000
DTSTAMP:20210125T083334Z
URL:https://www.i2m.univ-amu.fr/events/tensor-networks-for-machine-learnin
g-guillaume-rabusseau/
SUMMARY:Tensor networks for machine learning - Guillaume Rabusseau - Guilla
ume Rabusseau
DESCRIPTION:In this talk\, I will give an introduction to tensor networks a
nd give a very brief overview of three recent contributions from my group
aiming at going beyond classical tensor decomposition models using the ten
sor network formalism.\nTensors are high order generalization of vectors a
nd matrices. Similar to matrix factorization techniques\, one of the goal
of tensor decomposition techniques is to express a tensor as a product of
small factors\, thus reducing the number of parameters and potentially reg
ularizing machine learning models. While linear algebra is ubiquitous and
taught in most undergrad curriculum\, tensor and multilinear algebra can b
e daunting. In the first part of the talk\, I will try to give an easy and
accessible introduction to tensor methods using the tensor network formal
ism. Tensor networks are an intuitive diagrammatic notation allowing one t
o easily reason about complex operations on high-order tensors.\nIn the se
cond part of the talk\, I will very briefly give an overview of three rece
nt work from my group\, ranging from tensorizing random projections to stu
dying the VC dimension of tensor network models.\nBIO\nGuillaume Rabusseau
is an assistant professor at Univeristé de Montréal 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 Reasoning and Learning La
b at McGill University\, where he worked with Prakash Panangaden\, Joelle
Pineau and Doina Precup. He obtained his PhD in computer science in 2016 a
t Aix-Marseille University under the supervision of François Denis and Ha
chem Kadri. His research interests lie at the intersection of theoretical
computer science and machine learning\, and his work revolves around explo
ring inter-connections between tensors and machine learning to develop eff
icient learning methods for structured data relying on linear and multilin
ear algebra.\nVisio: https://univ-amu-fr.zoom.us/j/97958103420?pwd=MXJIMEs
rSTlvNnl6czNQcGFESkYwdz09
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:Site Nord\, CMI\, Salle de Séminaire R164 (1er étage)\, 39 Rue J
oliot 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=Site Nord\, 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