BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Gabriel Peyré (CNRS & École Normale Supérieure)
DTSTART:20210322T143000Z
DTEND:20210322T153000Z
DTSTAMP:20260423T035054Z
UID:OWOS/38
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/OWOS/38/">Sc
 aling Optimal Transport for High Dimensional Learning</a>\nby Gabriel Peyr
 é (CNRS & École Normale Supérieure) as part of One World Optimization s
 eminar\n\n\nAbstract\nOptimal transport (OT) has recently gained lot of in
 terest in machine learning. It is a natural tool to compare in a geometric
 ally faithful way probability distributions. It finds applications in both
  supervised learning (using geometric loss functions) and unsupervised lea
 rning (to perform generative model fitting). OT is however plagued by the 
 curse of dimensionality\, since it might require a number of samples which
  grows exponentially with the dimension. In this talk\, I will review entr
 opic regularization methods which define geometric loss functions approxim
 ating OT with a better sample complexity. More information and references 
 can be found on the website of our book "Computational Optimal Transport" 
 https://optimaltransport.github.io/\n\nThe address and password of the zoo
 m room of the seminar are sent by e-mail on the mailinglist of the seminar
  one day before each talk\n
LOCATION:https://researchseminars.org/talk/OWOS/38/
END:VEVENT
END:VCALENDAR