BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Statistics - ECPv5.1.6//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Statistics
X-ORIGINAL-URL:https://stat.wisc.edu
X-WR-CALDESC:Events for Department of Statistics
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20200308T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20201101T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20200923T100000
DTEND;TZID=America/Chicago:20200923T110000
DTSTAMP:20210125T212022
CREATED:20200812T183643Z
LAST-MODIFIED:20200909T185633Z
UID:3862-1600855200-1600858800@stat.wisc.edu
SUMMARY:Statistics Seminar
DESCRIPTION:Title: Learning with entropy-regularized optimal transport \nPresenter: Dr. Aude Genevay \nAbstract: Entropy-regularized OT (EOT) was first introduced by Cuturi in 2013 as a solution to the computational burden of OT for machine learning problems. In this talk\, after studying the properties of EOT\, we will introduce a new family of losses between probability measures called Sinkhorn Divergences. Based on EOT\, this family of losses actually interpolates between OT (no regularization) and MMD (infinite regularization). We will illustrate these theoretical claims on a set of learning problems formulated as minimizations over the space of measures \nLink: https://uwmadison.webex.com/meet/pr923156234
URL:https://stat.wisc.edu/event/statistics-seminar-5-2020-09-23/
END:VEVENT
END:VCALENDAR