BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250701T203729EDT-73299SeaKi@132.216.98.100
DTSTAMP:20250702T003729Z
DESCRIPTION:Title:  Measure estimation on manifolds through optimal transpo
 rt\n\nAbstract. The Wasserstein distances Wp are measures of similarity be
 tween probability distributions that have found numerous applications in m
 achine learning. For example\, Wasserstein Generative Adversarial Networks
  are able to generate realistic fake images by approximating the empirical
  distribution of a sample of images with respect to W1. From a statistical
  perspective\, the question of the estimation of quantities related to the
  optimal transport problem is then raised. We will present two settings wh
 ere one can bypass the curse of dimensionality. First\, in the case where 
 the target distribution is supported on a low-dimensional unknown submanif
 old. Second\, in the case where the target distribution is obtained as the
  pushforward of the gaussian distribution through some map that is known t
 o belong to a given functional class F. In the latter case\, we are able t
 o obtain fast rates of estimation that depend uniquely on the metric entro
 py of the class F.\n\nZoom: https://mcgill.zoom.us/j/82167352773?pwd=VHZPZ
 WQ0d1g1S3M0cnVvWW9jbWxEdz09\n
DTSTART:20221124T163000Z
DTEND:20221124T173000Z
LOCATION:Room 1214\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Vincent Divol (NYU)
URL:/mathstat/channels/event/vincent-divol-nyu-343756
END:VEVENT
END:VCALENDAR