BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Statistics - ECPv5.1.6//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Statistics
X-ORIGINAL-URL:https://stat.wisc.edu
X-WR-CALDESC:Events for Department of Statistics
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20200308T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20201101T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20200916T160000
DTEND;TZID=America/Chicago:20200916T170000
DTSTAMP:20210125T204328
CREATED:20200812T183643Z
LAST-MODIFIED:20200909T185605Z
UID:3861-1600272000-1600275600@stat.wisc.edu
SUMMARY:Statistics Seminar
DESCRIPTION:Title: Self-induced regularization: from linear regression to neural networks \nPresenter: Andrea Montanari \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] \nLink: https://uwmadison.webex.com/meet/pr923156234
URL:https://stat.wisc.edu/event/statistics-seminar-5-2020-09-16/
END:VEVENT
END:VCALENDAR