BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:39303135-6130-4930-b465-623166363933
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Entropy-regularized optimal transport and its connection with 
 score estimation - Soumik Pal\, Professor\, University of Washington
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20261101T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20241103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20251102T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20240310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20250309T020000
RDATE:20260308T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:01f4516b-33b0-4dcd-8aba-7418bfcb30b9
DTSTAMP:20260626T021314Z
CLASS:PUBLIC
CREATED:20241115T220940Z
DESCRIPTION:Abstract: Entropy-regularized optimal transport (EOT) is a popu
 lar version of the classical Monge-Kantorovich optimal transport problem. 
 The addition of entropy as a regularizer was introduced to provide smoothn
 ess\, robustness\, and computational efficiency. But\, in fact\, it does s
 o much more. I will focus on one striking aspect\, its connection with est
 imating the so-called score function (the gradient of the log density with
  respect to the argument). As an application we will talk about discretizi
 ng Wasserstein gradient flows by an iterated application of EOT. This last
  application is…
DTSTART;TZID=America/Vancouver:20241125T130000
DTEND;TZID=America/Vancouver:20241125T140000
LAST-MODIFIED:20241115T222217Z
LOCATION:UBC Vancouver Campus\, ICCS X836
SUMMARY:Entropy-regularized optimal transport and its connection with score
  estimation - Soumik Pal\, Professor\, University of Washington
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/entropy-regularized-optimal-transport-and-it
 s-connection-score-estimation-soumik-pal
END:VEVENT
END:VCALENDAR