BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Optimal Transport Metrics - Shreyas Padhy\, University of Cambridg
 e
DTSTART:20220209T110000Z
DTEND:20220209T123000Z
UID:TALK169037@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:The field of Optimal Transport (OT) is a powerful mathematical
  framework that provides a natural approach for comparing probability dist
 ributions. In recent years\, OT has emerged as a central topic in machine 
 learning\, largely due to the development of approximate OT solvers that c
 an scale to large dimensions and problems. In this talk\, we first briefly
  cover the historical and mathematical formulations of Optimal Transport t
 heory covering the works of Monge and Kantorovich\, and motivating Wassers
 tein distances. We then cover recent works that develop approximate\, scal
 able OT methods such as entropic regularisation\, Sinkhorn divergences and
  sliced Wasserstein distances. Finally\, we cover recent applications of O
 T to the field of machine learning for classification\, generative modelli
 ng\, and density estimation\, and briefly discuss extensions of OT to prob
 lems involving unbalanced transport (Wasserstein Fisher-Rao) and domain ad
 aptation (Gromov Wasserstein).\n\nReadings:\n\nPeyré G\, Cuturi M. Comput
 ational optimal transport: With applications to data science. Foundations 
 and Trends® in Machine Learning. 2019 Feb 11\;11(5-6):355-607.\n\nOur rea
 ding groups are livestreamed via Zoom and recorded for our Youtube channel
 . The Zoom details are distributed via our weekly mailing list.
LOCATION: Cambridge University Engineering Department \,LR3A
END:VEVENT
END:VCALENDAR