BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IEM Distinguished Lecturers Seminar: Frugality in machine learning
 : sparsity\, a value for the future?
DTSTART:20240524T131500
DTEND:20240524T140000
DTSTAMP:20260427T200457Z
UID:17b65ba3afc1923c9669d0b5497df5129c24702211dd0022a28b7dcb
CATEGORIES:Conferences - Seminars
DESCRIPTION:Rémi Gribonval\, Research Director with Inria\, Inria & ENS L
 yon\, France\nThe seminar will take place in ELA 1 and will be simultaneou
 sly broadcasted in Neuchâtel Campus MC B1 273.\n\nCoffee and cookies wi
 ll be served from 13:00.\n\nAbstract\nSparse vectors and sparse matrices p
 lay a transerve role in signal and image processing: they have led to succ
 esful approaches efficiently addressing tasks as diverse as data compressi
 on\, fast transforms\, signal denoising and source separation\, or more ge
 nerally inverse problems.\nTo what extent can the potential of sparsity be
  also leveraged to achieve more frugal (deep) learning techniques?\nThroug
 h an overview of recent explorations around this theme\, I will compare an
 d contrast classical sparse regularization for inverse problems with its n
 atural extensions that aim at learning neural networks with sparse connect
 ions. During our journey\, I will notably highlight the role of rescaling-
 invariances of modern deep parameterizations\, which come with their curse
 s and blessings.\n\nShort biography\nRémi Gribonval is a Research Directo
 r (Directeur de Recherche) with Inria and the head of the OCKHAM research 
 group of Laboratoire de l’Informatique du Parallélisme at École Normal
 e Supérieure de Lyon. He is the former scientific leader of the PANAMA re
 search group on sparse audio processing at IRISA\, Rennes\, France. In 201
 1\, he was awarded the Blaise Pascal Award of the GAMNI-SMAI by the French
  Academy of Sciences\, and a starting investigator grant from the European
  Research Council in 2011. He is an IEEE fellow and a EURASIP Fellow. He f
 ounded the series of international workshops SPARS on Signal Processing wi
 th Adaptive/Sparse Representations.
LOCATION:ELA 1 https://plan.epfl.ch/?room==ELA%201 https://epfl.zoom.us/j/
 67317987786
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR