BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250925T120000
DTEND;TZID=America/New_York:20250925T130000
DTSTAMP:20260602T001158
CREATED:20250828T173345Z
LAST-MODIFIED:20250828T173345Z
UID:20936-1758801600-1758805200@seasevents.nmsdev7.com
SUMMARY:FOLDS seminar: Propagation-of-Chaos in Shallow Neural Networks beyond Logarithmic Time.
DESCRIPTION:Zoom link: https://upenn.zoom.us/j/98220304722 \nThe analysis of gradient-based learning of Neural Networks remains an outstanding challenge\, even for the simplest shallow architectures. \nA powerful mathematical framework that has emerged over recent years lifts the optimization in the space of probability measures\, and captures important empirical phenomena such as the ‘blessing of overparametrization’. However\, the resulting learning guarantees remain mostly qualitative. \nIn this talk\, we study the fluctuations between idealized mean-field dynamics and polynomially-sized networks over suitable time horizons — the so-called Propagation of Chaos. We provide a novel analysis that goes beyond traditional Gronwall-based PoC by exploiting certain geometric properties of the optimization landscape\, and apply these results to representative models such as single-index models\, establishing polynomial learning guarantees.\nJoint work with Margalit Glasgow and Denny Wu.\n 
URL:https://seasevents.nmsdev7.com/event/folds-seminar-tba-2/
LOCATION:Amy Gutmann Hall\, Room 414\, 3333 Chestnut Street\, Philadelphia\, 19104\, United States
CATEGORIES:Seminar,Colloquium
END:VEVENT
END:VCALENDAR