BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Jevgenija Rudzusika (KTH Stockholm)
DTSTART:20210720T101500Z
DTEND:20210720T114500Z
DTSTAMP:20260423T022602Z
UID:MathDeep/14
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/MathDeep/14/
 ">Accelerated Forward-Backward Optimization using Deep Learning</a>\nby Je
 vgenija Rudzusika (KTH Stockholm) as part of Mathematics of Deep Learning\
 n\n\nAbstract\nWe propose several deep-learning accelerated optimization s
 olvers with convergence guarantees. We use ideas from the analysis of acce
 lerated forward-backward schemes like FISTA\, but instead of the classical
  approach of proving convergence for a choice of parameters\, such as a st
 ep-size\, we show convergence whenever the update is chosen in a specific 
 set. Rather than picking a point in this set using some predefined method\
 , we train a deep neural network to pick the best update. Finally\, we sho
 w that the method is applicable to several cases of smooth and non-smooth 
 optimization and show superior results to established accelerated solvers.
 \n
LOCATION:https://researchseminars.org/talk/MathDeep/14/
END:VEVENT
END:VCALENDAR