BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Département de mathématiques et applications - ECPv6.2.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.math.ens.psl.eu
X-WR-CALDESC:évènements pour Département de mathématiques et applications
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20221030T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20220512T113000
DTEND;TZID=Europe/Paris:20220512T123000
DTSTAMP:20260525T084322
CREATED:20220530T111420Z
LAST-MODIFIED:20220530T112029Z
UID:15615-1652355000-1652358600@www.math.ens.psl.eu
SUMMARY:Effective dynamics and critical scaling for Stochastic Gradient Descent in high dimensions -  Gerard Ben Arous (New York University)
DESCRIPTION:Gerard Ben Arous (New York University)\n \nTitle: Effective dynamics and critical scaling for Stochastic Gradient Descent in high dimensions\n \nAbstract: SGD in high dimension is a workhorse for high dimensional statistics and machine learning\, but understanding its behavior in high dimensions is not yet a simple task. We study here the limiting ‘effective’ dynamics of some summary statistics for SGD in high dimensions\, and find interesting and new regimes\, i.e. not the expected one given by the population gradient flow. We find that a new corrector term is needed and that the phase portrait of these dynamics is substantially different from what would be predicted using the classical approach including for simple tasks. (joint work with Reza Gheissari (UC Berkeley) and Aukosh Jagannath (Waterloo))
URL:https://www.math.ens.psl.eu/evenement/learning-to-predict-complex-outputs-a-kernel-view-gerard-ben-arous-new-york-university/
LOCATION:Amphi Jaurès (29 Rue d’Ulm)
CATEGORIES:Séminaire Data de l’ENS
END:VEVENT
END:VCALENDAR