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:20260403T100524
DTSTART;TZID=America/Detroit:20260417T100000
DTEND;TZID=America/Detroit:20260417T110000
SUMMARY:Workshop / Seminar:Statistics Department Seminar Series: Yuting Wei\, Associate Professor\, Department of Statistics & Data Science\, University of Pennsylvania
DESCRIPTION:The score-based diffusion models have become a cornerstone of modern generative AI. While recent works aim to develop sharp convergence guarantees\, the iteration complexity of existing analyses typically scales with the ambient data dimension $d$ of the target distribution\, leading to overly conservative theory that fails to explain its practical efficiency. This motivates us to understand how diffusion models can achieve sampling speed-ups through automatic exploitation of intrinsic low dimensionality of data for both continuous and discrete distributions.  \n\nThis talk explores two key scenarios: (1) For a broad class of continous distributions with intrinsic dimension $k$\, we show that the iteration complexity of the denoising diffusion probabilistic model (DDPM) scales nearly linearly with $k$\, which is optimal under the KL divergence metric\; (2) For masking discrete diffusions\, under a continuous-time Markov chain (CTMC) formulation\, we introduce a modified $\tau$-leaping sampler whose convergence rate is governed by an intrinsic information-theoretic quantity\, termed the \emph{effective total correlation}\, which is upper bounded by $d \log S$ (with $S$ the vocabulary size) but can be sublinear or even constant for structured discrete distributions.
UID:146703-21899508@events.umich.edu
URL:https://events.umich.edu/event/146703
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:seminar
LOCATION:West Hall - 340
CONTACT:
END:VEVENT
END:VCALENDAR