BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Sparse and Spurious: Dictionary Learning with Noise and Outliers
DTSTART:20150223T161500
DTSTAMP:20260407T175719Z
UID:cc48599924efffbcb41905d77b178a4b3cd12bbd7a00a42f6118e1ef
CATEGORIES:Conferences - Seminars
DESCRIPTION:Rémi Gribonval / PANAMA / INRIA Rennes\nBio: Rémi Gribonval 
 is a Research Director (Directeur de Recherche) with INRIA in Rennes\, Fra
 nce\, and the scientific leader of the PANAMA research group on sparse aud
 io processing. In 2011\, he was awarded the Blaise Pascal Award of the GAM
 NI-SMAI by the French Academy of Sciences\, and a starting investigator gr
 ant from the European Research Council in 2011. He is an IEEE fellow. He f
 ounded the series of international workshops SPARS on Signal Processing wi
 th Adaptive/Sparse Representations. Since 2002 he has been the coordinator
  of several national\, bilateral and European research projects. He is cur
 rently a member of the LVA/ICA steering committee\, the IEEE SPTM Technica
 l Committee\, and the SPARS steering committee.\nRémi Gribonval was a stu
 dent at Ecole Normale Supérieure\, Paris from 1993 to 1997. He received t
 he Ph. D. degree in applied mathematics from the University of Paris-IX Da
 uphine\, Paris\, France\, in 1999\, and his Habilitation à Diriger des Re
 cherches in applied mathematics from the University of Rennes I\, Rennes\,
  France\, in 2007.\nMany tasks\, ranging from the resolution of inverse pr
 oblems to denoising\, can be efficiently addressed assuming some sparse mo
 del with an overcomplete dictionary. In the last decade\, the statistical 
 and algorithmic analysis of these approaches has become quite mature. Yet\
 , the choice of the dictionary for a given problem remains a key practical
  issue\, empirically addressed through data-driven principles known as dic
 tionary learning.\nThe talk will first briefly review dictionary learning 
 and related sparse matrix factorizations\,  then I will describe recently
  obtained generalization bounds and identifiability guarantees for diction
 ary learning in the presence of noise and outliers.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR