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:20260901T000414
DTSTART;TZID=America/Detroit:20260902T160000
DTEND;TZID=America/Detroit:20260902T180000
SUMMARY:Fair / Festival:Find us at Festifall!
DESCRIPTION:Find us at table C-85 Outside of Hatcher Grad. Library!
UID:151255-21911250@events.umich.edu
URL:https://events.umich.edu/event/151255
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:
LOCATION:Diag
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260820T232857
DTSTART;TZID=America/Detroit:20260902T160000
DTEND;TZID=America/Detroit:20260902T170000
SUMMARY:Workshop / Seminar:Theory and Methods for Conditional Diffusion Models
DESCRIPTION:will study conditional sampling with diffusion models under linear constraints\, with a focus on understanding how a pre-trained unconditional diffusion model can be used to sample from a conditional distribution. I will present a normal–tangent decomposition of the conditional score that separates the effect of the observed constraints from the remaining uncertainty in the distribution. This decomposition provides a way to characterize the discrepancy between the unconditional and conditional diffusion dynamics\, and to relate this discrepancy to information-theoretic quantities.\n\nBased on this perspective\, I will introduce a sampling method that combines projected Langevin initialization on the constraint set with guided reverse diffusion. I will discuss theoretical and information-theoretic guarantees for the resulting sampler\, as well as numerical results illustrating its behavior on linear inverse problems. At the end\, I will also briefly discuss related results showing how the information content and structural properties of a target distribution can reduce the dependence of diffusion sampling on the ambient dimension.
UID:150579-21909651@events.umich.edu
URL:https://events.umich.edu/event/150579
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Mathematics
LOCATION:East Hall - 1360
CONTACT:
END:VEVENT
END:VCALENDAR