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:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20250331T140000
DTEND;TZID=Europe/Helsinki:20250331T140000
DTSTAMP:20260710T074006
CREATED:20250318T071551Z
LAST-MODIFIED:20250327T133149Z
UID:17966-1743429600-1743429600@crest.science
SUMMARY:Loucas PILLAUD-VIVIEN (Ecole des Ponts) - Learning Gausssian multi-index models via gradient flow
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: 31th March\nPlace: 3001 \n  \nLoucas PILLAUD-VIVIEN – Learning Gausssian multi-index models via gradient flow \n  \n  \n Abstract:  \nWe study gradient flow on the multi-index regression problem for high-dimensional Gaussian data. Multi-index functions consist of a composition of an unknown low-rank linear projection and an arbitrary unknown\, low-dimensional link function. As such\, they constitute a natural template for feature learning in neural networks. We consider a two-timescale algorithm\, whereby the low-dimensional link function is learnt with a non-parametric model infinitely faster than the subspace parametrizing the low-rank projection. By appropriately exploiting the matrix semigroup structure arising over the subspace correlation matrices\, we establish global convergence of the resulting Grassmannian population gradient flow dynamics\, and provide a quantitative description of its associated ‘saddle-to-saddle’ dynamics. \n  \nOrganizers: \nAnna KORBA (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/loucas-pillaud-vivien-ecole-des-ponts-tba/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR