BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Rate estimates for total variation distance - Miklos Rasonyi (HUN-
 REN Renyi Institute)
DTSTART:20240719T150000Z
DTEND:20240719T160000Z
UID:TALK219079@talks.cam.ac.uk
DESCRIPTION:For algorithms of machine learning\, rate estimates are often 
 provided in the Wasserstein metric or some variant thereof. There has been
  spectacular recent progress in the techniques for establishing such estim
 ates.At the same time\, powerful methods have been developed in Malliavin 
 calculus that enable to infer total variation convergence from weak conver
 gence.After presenting an overview of the developments above\, we show som
 e new results on total variation convergence that do not rely on Malliavin
  calculus nevertheless they are applicable to various discrete-time numeri
 cal schemes.\nThis talk is based on joint work with I. Ivkovic.\n&nbsp\;
LOCATION:External
END:VEVENT
END:VCALENDAR