BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//College of Engineering - University of Wisconsin-Madison - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:College of Engineering - University of Wisconsin-Madison
X-ORIGINAL-URL:https://engineering.wisc.edu
X-WR-CALDESC:Events for College of Engineering - University of Wisconsin-Madison
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20240310T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20241103T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20250309T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20251102T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20260308T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20261101T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20251010T120000
DTEND;TZID=America/Chicago:20251010T130000
DTSTAMP:20260429T011340
CREATED:20250929T154550Z
LAST-MODIFIED:20250929T154957Z
UID:10001337-1760097600-1760101200@engineering.wisc.edu
SUMMARY:Understanding Generalization of Diffusion Models: Structured Data and Memorization
DESCRIPTION:UW-ISyE looks forward to welcoming Minshuo Chen\, assistant professor with the Department of Industrial Engineering & Management Sciences at Northwestern University \n\n\n\n\n\n\n\nDiffusion models achieve state-of-the-art performance in various high-dimensional data modeling tasks. These empirical successes challenge conventional wisdom while raising critical concerns. On the one hand\, in high-dimensional applications\, diffusion models’ strong performance appears to circumvent the curse of dimensionality. On the other hand\, memorization emerges as an unwanted byproduct\, limiting creativity and raising safety and privacy issues. In this talk\, we theoretically decipher these observations. The first part develops statistical learning guarantees of diffusion models for low-dimensional manifold data—an assumption aligns well with many practical datasets. We prove that diffusion models can learn data distributions at rates governed by the intrinsic dimension and curvature of the data. The second part establishes separation in memorization and generalization through the statistical learning and network approximation lens. Building on these insights\, we propose a pruning-based method that reduces memorization while maintaining generation quality. \n\n\n\n\n\nBio: Minshuo Chen is an assistant professor with the Department of Industrial Engineering & Management Sciences at Northwestern University. He was an associate research scholar with the Department of Electrical and Computer Engineering at Princeton University from 2022 to 2024. He completed his Ph.D. from the School of Industrial and Systems Engineering at Georgia Tech\, majoring in Machine Learning. His research focuses on developing principled methodologies and theoretical foundations of deep learning\, with a particular interest in 1) generative models including diffusion models\, 2) foundations of machine learning\, such as optimization and sample efficiency\, and 3) reinforcement learning.
URL:https://engineering.wisc.edu/event/understanding-generalization-of-diffusion-models-structured-data-and-memorization/
LOCATION:1163 Mechanical Engineering\, 1513 Engineering Dr.\, Madison\, WI\, 53706\, United States
CATEGORIES:Colloquium,Industrial & Systems Engineering
ATTACH;FMTTYPE=image/png:https://engineering.wisc.edu/wp-content/uploads/2025/09/chengraphic.avif
END:VEVENT
END:VCALENDAR