BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen - ECPv5.7.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
X-ORIGINAL-URL:https://www.greyc.fr
X-WR-CALDESC:évènements pour GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20221030T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20221201T140000
DTEND;TZID=Europe/Paris:20221201T160000
DTSTAMP:20260423T093624
CREATED:20221110T163447Z
LAST-MODIFIED:20230307T084135Z
UID:10997-1669903200-1669910400@www.greyc.fr
SUMMARY:Séminaire IMAGE : Antonio Silveti-Falls (CentraleSupélec)\, « Nonsmooth Implicit Differentiation for Machine Learning and Optimization »
DESCRIPTION:Nous aurons le plaisir d’accueillir Antonio Silveti-Falls\, MC CentraleSupélec/Université de Paris-Saclay au Centre pour la Vision Numérique (et ancien doctorant de l’équipe IMAGE!).\nIl donnera un séminaire IMAGE\, le jeudi 1 décembre à 14h00\, en salle F-200.\n\nTitre : Nonsmooth Implicit Differentiation for Machine Learning and Optimization\nRésumé :\nWe present a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e.\, semialgebraic/definable problems) provided that a nonsmooth form of the classical invertibility condition is fulfilled. This approach allows for formal subdifferentiation: for instance\, replacing derivatives by Clarke Jacobians in the usual differentiation formulas is fully justified for a wide class of nonsmooth problems. Moreover this calculus is entirely compatible with algorithmic differentiation (e.g.\, backpropagation)\, which currently underlies all modern deep learning methods. We discuss applications and pathologies when our hypotheses are violated.\n\nVenez nombreux!
URL:https://www.greyc.fr/event/seminaire-image-antonio-silveti-falls-centralesupelec-nonsmooth-implicit-differentiation-for-machine-learning-and-optimization/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:General,Image,Seminaire Image
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20221209T140000
DTEND;TZID=Europe/Paris:20221209T153000
DTSTAMP:20260423T093624
CREATED:20221123T094951Z
LAST-MODIFIED:20230307T085426Z
UID:11010-1670594400-1670599800@www.greyc.fr
SUMMARY:Séminaire IMAGE : Radu-Alexandru Dragomir (EPFL)\, « Optimization methods for large non-quadratic problems »
DESCRIPTION:Nous aurons le plaisir d’accueillir Radu-Alexandru Dragomir \, post-doctorant à l’EPFL et candidat au concours CR CNRS 2023 dans l’équipe IMAGE.\nIl donnera un séminaire IMAGE\, le vendredi 9 décembre à 14h00\, en salle F-200.\n\nTitre : Optimization methods for large non-quadratic problems\n\nRésumé :\nIn this talk\, I will give an overview of my research interests. I study optimization problems with highly non-quadratic geometry\, such as nonlinear least squares or Poisson deblurring. I particularly focus on the class of quadratic inverse problems arising in low-rank minimization\, sensor network localization and phase retrieval. In these problems\, the objective functions is a quartic polynomial; a thorough analysis of this structure allows to design well-adapted algorithms\, and understand their optimization and statistical properties.\n \n 
URL:https://www.greyc.fr/event/seminaire-image-radu-alexandru-dragomir-epfl-optimization-methods-for-large-non-quadratic-problems/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:General,Image,Seminaire Image
END:VEVENT
END:VCALENDAR