BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//College of Engineering - University of Wisconsin-Madison - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
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: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
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20270314T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20271107T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20260129T120000
DTEND;TZID=America/Chicago:20260129T130000
DTSTAMP:20260525T221913
CREATED:20260121T184709Z
LAST-MODIFIED:20260121T184711Z
UID:10001441-1769688000-1769691600@engineering.wisc.edu
SUMMARY:ISyE - Finding the needle in the haystack: How gradient descent converges to low-dimensional solutions in over-parameterized models.
DESCRIPTION:In contemporary machine learning\, realistic models exhibit increasing nonconvexity and overwhelming overparameterization. This nonconvex nature often leads to numerous undesirable or “spurious” local solutions\, while overparameterization exacerbates the risk of overfitting. Yet\, simple “short-sighted” algorithms\, such as gradient descent (GD) or its variants\, often find the needle in the haystack: they converge to the correct\, low-dimensional solutions even when such structures are neither explicitly encoded in the model nor required by the algorithm. This talk delves into explaining this desirable performance of GD-based algorithms by studying their fine-grained trajectory on over-parameterized models\, spanning from low-rank models to deep neural networks.   \n\n\n\n\n\nBio: Salar Fattahi is an Assistant Professor of Industrial and Operations Engineering at the University of Michigan. He received his Ph.D. from the University of California\, Berkeley in 2020. He is the recipient of a National Science Foundation CAREER Award and the Deans’ MLK Spirit Award. His research focuses on optimization and machine learning and has been recognized with multiple nominations and awards\, including the INFORMS Junior Faculty Interest Group Best Paper Award\, the INFORMS Data Mining Best Paper Award\, and the INFORMS Computing Society Best Student Paper Award. He currently serves as Vice Chair for Machine Learning in the INFORMS Optimization Society\, as an Associate Editor for the INFORMS Journal on Data Science\, and as an Area Chair for several premier conferences\, including NeurIPS\, ICML\, and ICLR.
URL:https://engineering.wisc.edu/event/isye-finding-the-needle-in-the-haystack-how-gradient-descent-converges-to-low-dimensional-solutions-in-over-parameterized-models/
LOCATION:2188 Mechanical Engineering Building\, 1513 University Avenue\, Madison\, WI\, 53706\, United States
CATEGORIES:Colloquium,Industrial & Systems Engineering
ATTACH;FMTTYPE=image/png:https://engineering.wisc.edu/wp-content/uploads/2026/01/fattahigraphic.avif
END:VEVENT
END:VCALENDAR