BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Progress Towards Understanding Generalization in Deep Learning - G
 intare Karolina Dziugaite\, Element AI 
DTSTART:20210413T140000Z
DTEND:20210413T150000Z
UID:TALK158926@talks.cam.ac.uk
CONTACT:96082
DESCRIPTION:There is\, as yet\, no satisfying theory explaining why common
  learning algorithms\, like those based on stochastic gradient descent\, g
 eneralize in practice on overparameterized neural networks. I will discuss
  various approaches that have been taken to explaining generalization in d
 eep learning\, and identify some of the barriers these approaches faced. I
  will then discuss my recent work on information-theoretic and PAC Bayesia
 n approaches to understanding generalization in noisy variants of SGD. In 
 particular\, I will highlight how we can take advantage of conditioning to
  obtain sharper data   and distribution-dependent generalization measures.
  I will also briefly touch upon my work on properties of the optimization 
 landscape and some of the challenges we face incorporating these insights 
 into the theory of generalization.
LOCATION:https://us02web.zoom.us/j/83327945534?pwd=SlRTcjVDTVFsNXRNdEczbys
 vSkpPdz09
END:VEVENT
END:VCALENDAR