BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Can kernel machines be a viable alternative to deep neural network
 s? - Dr Parthe Pandit\, Indian Institute of Technology\, Bombay
DTSTART:20250225T140000Z
DTEND:20250225T150000Z
UID:TALK228385@talks.cam.ac.uk
CONTACT:Prof. Ramji Venkataramanan
DESCRIPTION:Deep learning remains an art with several heuristics that do n
 ot always translate across application domains. Kernel machines\, a classi
 cal model in ML\, have received renewed attention following the discovery 
 of the Neural Tangent Kernel and its equivalence to wide neural networks. 
 I will present 2 results which show the promise of kernel machines for mod
 ern large scale applications.\n1. Data-dependent supervised kernels: https
 ://www.science.org/stoken/author-tokens/ST-1738/full\n2. Fast scalable tra
 ining algorithms for kernel machines: https://arxiv.org/abs/2411.16658\n\n
 *Bio*: Parthe Pandit is the Thakur Family Chair Assistant Professor at the
  Center for Machine Intelligence and Data Science at IIT Bombay. He was a 
 Simons Postdoctoral Fellow at UC San Diego. He obtained his PhD from UCLA 
 and his undergraduate education from IIT Bombay. In 2024\, he was awarded 
 the AI2050 Early Career Fellowship by Schmidt Sciences. He has also been t
 he recipient of the 2019 Jack K Wolf Student paper award by the IEEE Infor
 mation Theory Society.
LOCATION:JDB Seminar Room\, CUED
END:VEVENT
END:VCALENDAR