BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Samuel Hurault\,  Convergence analysis of Plug-and-Play algorithms
  for image inverse problems
DTSTART:20250407T080000Z
DTEND:20250407T090000Z
DTSTAMP:20260310T063200Z
UID:indico-event-12619@indico.math.cnrs.fr
CONTACT:mazari@ceremade.dauphine.fr
DESCRIPTION:Speakers: Samuel Hurault\n\nAbstract : Plug-and-play (PnP) met
 hods are a class of iterative algorithms for imaging inverse problems\, le
 veraging off-the-shelf Gaussian denoisers for regularization. These method
 s achieve impressive visual results\, especially when deep neural networks
  parameterize the denoisers. However\, the theoretical convergence of PnP 
 methods has yet to be fully established. This talk provides an overview of
  the PnP literature\, introduces new convergence results for PnP algorithm
 s when paired with specific denoisers\, and finally\, presents a novel Bre
 gman version of Plug-and-Play.\n\nhttps://indico.math.cnrs.fr/event/12619/
LOCATION:A711 (Université Paris-Dauphine)
URL:https://indico.math.cnrs.fr/event/12619/
END:VEVENT
END:VCALENDAR