BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1640
DTSTAMP:20260119T062659Z
SUMMARY:Old dog\, Old tricks\, New show: Fast preconditioned 1st order meth
 ods for training Kernel Machines
DESCRIPTION:Speaker: Parthe Pandit (IIT Bombay)\n\nAbstract: \nKernel Machi
 nes are a classical family of models in Machine Learning that overcome sev
 eral limitations of Neural Networks. These models have regained popularity
  following some landmark results showing their equivalence to Neural Netwo
 rks. I will present a suite of training algorithms for this family of mode
 ls based on preconditioned stochastic gradient descent in the Reproducing 
 Kernel Hilbert Space (RKHS). These algorithms\, called EigenPro\, are stat
 e of the art for training of Kernel Machines at scale. They have enabled t
 he training of very large models with arbitrarily large datasets. \n \nS
 hort Bio:  Parthe Pandit is a Thakur Family Chair Assistant Professor at 
 C-MInDS\, IIT Bombay. He was a Simons postdoctoral fellow at UC San Diego\
 , obtained his PhD and MS from UCLA\, and his undergraduate education from
  IIT Bombay. He received the AI2050 Early Career Fellowship from Schmidt S
 ciences in 2024\, and the Jack K Wolf Student Paper Award at ISIT 2019.\n
URL:https://www.tcs.tifr.res.in/web/events/1640
DTSTART;TZID=Asia/Kolkata:20260120T160000
DTEND;TZID=Asia/Kolkata:20260120T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR