BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CMSA
X-ORIGINAL-URL:https://cmsa.fas.harvard.edu
X-WR-CALDESC:Events for CMSA
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:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20200923T150000
DTEND;TZID=America/New_York:20200923T160000
DTSTAMP:20240515T201416Z
CREATED:20240209T014918Z
LAST-MODIFIED:20240515T201416Z
UID:10001784-1600873200-1600876800@cmsa.fas.harvard.edu
SUMMARY:Self-induced regularization from linear regression to neural networks
DESCRIPTION:Speaker: Andrea Montanari\, Departments of Electrical Engineering and Statistics\, Stanford \nTitle: Self-induced regularization from linear regression to neural networks \nAbstract: Modern machine learning methods –most noticeably multi-layer neural networks– require to fit highly non-linear models comprising tens of thousands to millions of parameters. Despite this\, little attention is paid to the regularization mechanism to control model’s complexity. Indeed\, the resulting models are often so complex as to achieve vanishing training error: they interpolate the data. Despite this\, these models generalize well to unseen data : they have small test error. I will discuss several examples of this phenomenon\, beginning with a simple linear regression model\, and ending with two-layers neural networks in the so-called lazy regime. For these examples precise asymptotics could be determined mathematically\, using tools from random matrix theory. I will try to extract a unifying picture. A common feature is the fact that a complex unregularized nonlinear model becomes essentially equivalent to a simpler model\, which is however regularized in a non-trivial way. [Based on joint papers with: Behrooz Ghorbani\, Song Mei\, Theodor Misiakiewicz\, Feng Ruan\, Youngtak Sohn\, Jun Yan\, Yiqiao Zhong] \n  \n 
URL:https://cmsa.fas.harvard.edu/event/9-23-2020-new-tech-in-mathematics-seminar/
LOCATION:Virtual
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-New-Technologies-in-Mathematics-09.23.20.png
END:VEVENT
END:VCALENDAR