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:20250114T110443
DTSTART;TZID=America/Detroit:20250128T160000
DTEND;TZID=America/Detroit:20250128T170000
SUMMARY:Workshop / Seminar:Statistics Department Seminar Series: Yuchen Wu\, Postdoctoral Research Fellow\, Department of Statistics and Data Science\, The Wharton School\, University of Pennsylvania
DESCRIPTION:Abstract:  Sampling from a target distribution is a recurring theme in statistics and generative artificial intelligence (AI). In statistics\, posterior sampling offers a flexible inferential framework\, enabling uncertainty quantification\, probabilistic prediction\, as well as the estimation of intractable quantities. In generative AI\, sampling aims to generate unseen instances that emulate a target population\, such as the natural distributions of texts\, images\, and molecules. \n\nIn this talk\, I will present my works on designing provably efficient sampling algorithms\, addressing challenges in both statistics and generative AI. (1) In the first part\, I will focus on posterior sampling for Bayes sparse regression. In general\, such posteriors are high-dimensional and contain many modes\, making them challenging to sample from. To address this\, we develop a novel sampling algorithm based on decomposing the target posterior into a log-concave mixture of simple distributions\, reducing sampling from a complex distribution to sampling from a tractable log-concave one. We establish provable guarantees for our method in a challenging regime that was previously intractable. (2) In the second part\, I will describe a training-free acceleration method for diffusion models\, which are deep generative models that underpin cutting-edge applications such as AlphaFold\, DALL-E and Sora. Our approach is simple to implement\, wraps around any pre-trained diffusion model\, and comes with a provable convergence rate that strengthens prior theoretical results. We demonstrate the effectiveness of our method on several real-world image generation tasks. \n\nLastly\, I will outline my vision for bridging the fields of statistics and generative AI\, exploring how insights from one domain can drive progress in the other.\n\nhttps://wuyc0114.github.io/
UID:129242-21862370@events.umich.edu
URL:https://events.umich.edu/event/129242
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:seminar
LOCATION:West Hall - 411
CONTACT:
END:VEVENT
END:VCALENDAR