BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240208T102318
DTSTART;TZID=America/Detroit:20240308T100000
DTEND;TZID=America/Detroit:20240308T110000
SUMMARY:Workshop / Seminar:Department Seminar Series: Éric Moulines\, Professor\, Department of Statistics\, Ecole Polytechnique
DESCRIPTION:Abstract:  The interest in using Denoising Diffusion Models (DDM) as priors for solving Bayesian inverse problems has increased rapidly in recent time.  However\, sampling from the resulting posterior distribution is a challenge. To address this problem\, previous works have proposed approximations to skew the drift term of the diffusion. In this work\, we take a different approach and utilize the specific structure of the DDM prior to define a set of intermediate and simpler posterior sampling problems\, resulting in a lower approximation error compared to previous methods. We empirically demonstrate the reconstruction capability of our method for general linear inverse problems on the basis of synthetic examples and various image restoration tasks.
UID:118605-21841279@events.umich.edu
URL:https://events.umich.edu/event/118605
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:seminar
LOCATION:West Hall - 340
CONTACT:
END:VEVENT
END:VCALENDAR