BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20240329T140000
DTEND;TZID=Europe/Helsinki:20240329T151500
DTSTAMP:20260710T205602
CREATED:20240320T090919Z
LAST-MODIFIED:20240322T105712Z
UID:16858-1711720800-1711725300@crest.science
SUMMARY:Ludovic STEPHAN (EPFL) - Feature learning in two-layer neural networks with large gradient steps
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 29th March 2024\nPlace : 3001 \n  \nLudovic STEPHAN (EPFL) – Feature learning in two-layer neural networks with large gradient steps \n  \nAbstract:  \nFeature learning is an important mechanism of neural networks\, and an integral part of their advantages over simpler (e.g. kernel) learning methods. In this talk\, I will present how this phenomenon occurs in two-layer networks trained with large gradient steps\, in which both the batch size and the learning rate grow polynomially with the dimension. In particular\, we uncover an occurence of the so-called “staircase” property of learning\, where important directions are learned sequentially at each new step. \n  \n  \nOrganizers:\nJaouad MOURTADA (CREST)\, Anna KORBA (CREST)\, Karim LOUNICI (CMAP) \n  \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/vincent-divol-universite-paris-dauphine-entropic-estimation-of-optimal-transport-maps-in-the-semi-discrete-case/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR