BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: Optimal Transport for Machine Learning - Gabriel Peyré — Écol
 e Normale Superieure
DTSTART:20191122T140000Z
DTEND:20191122T150000Z
UID:TALK130069@talks.cam.ac.uk
CONTACT:Dr Sergio Bacallado
DESCRIPTION:Optimal transport (OT) has become a fundamental mathematical t
 ool at the interface between optimization\, partial differential equations
  and probability. It has recently emerged as an important approach to tack
 le a surprisingly wide range of applications\, such as shape registration 
 in medical imaging\, structured prediction in supervised learning and the 
 training of deep generative networks. In this talk\, I will review an emer
 ging class of numerical approaches for the approximate resolution of OT-ba
 sed optimization problems. This offers a new perspective to scale OT for h
 igh dimensional problems in machine learning. More information and referen
 ces can be found on the website of our book "Computational Optimal Transpo
 rt" https://optimaltransport.github.io/
LOCATION:MR12
END:VEVENT
END:VCALENDAR