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:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20260629T140000
DTEND;TZID=Europe/Helsinki:20260629T153000
DTSTAMP:20260709T171928
CREATED:20260223T141458Z
LAST-MODIFIED:20260624T072244Z
UID:18826-1782741600-1782747000@crest.science
SUMMARY:Andrea MONTANARI (Stanford University) - Learning in two-layer neural networks: A statistical overview
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: 29th June\nPlace: 3001 \n  \nAndrea MONTANARI (Stanford University) – Learning in two-layer neural networks: A statistical overview \n  \n Abstract:  \nClassical statistical models are constructed so that either the number of parameters is small with respect to the sample size\, or they regularization is strong enough so that their `effective dimension’ is small. From this perspective\, basic techniques such as maximum likelihood are not that different from more modern ones\, such as the Lasso. \nIn contrast\, modern machine learning models are vastly miss-specified and overparametrized\, and only very loosely regularized. The resulting emirical risk function has many near-global optima\, which are very far from each other in parameters’ space. How can we make sense of their statistical properties? I will summarize what we learnt over the years by studying a simple and yet extremely rich setting: learning in two-layer networks. \n  \n  \nOrganizers: \nAnna KORBA (CREST)\, Vincent DIVOL (CREST) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/andrea-montanari-stanford-university-tba-2/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR