BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1800
DTSTAMP:20261112T070108Z
SUMMARY:There Are Only Two Algorithms in Online Learning
DESCRIPTION:Speaker: Aakash Ghosh (TIFR)\n\nAbstract: \nOnline convex optim
 ization seems to have an endless zoo of algorithms: Online Gradient Descen
 t\, Follow the Regularized Leader\, Multiplicative Weights\, Mirror Descen
 t\, and many more. But how different are these algorithms\, really?In this
  talk\, we'll try to dismantle this zoo\, one algorithm at a time. We'll s
 tart by seeing why linear losses are essentially all we need to understand
  online convex optimization. Then we'll introduce two seemingly different 
 philosophies for making decisions: following the gradient and following th
 e (regularized) leader. Surprisingly\, these often turn out to be two ways
  of describing the same algorithm. Finally\, we'll see how changing a regu
 larizer gives rise to apparently different algorithms\, including Multipli
 cative Weights.\n
URL:https://www.tcs.tifr.res.in/web/events/1800
DTSTART;TZID=Asia/Kolkata:20261113T160000
DTEND;TZID=Asia/Kolkata:20261113T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR