BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
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:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20231101T153000
DTEND;TZID=America/New_York:20231101T163000
DTSTAMP:20260720T154956
CREATED:20240223T054758Z
LAST-MODIFIED:20240223T054856Z
UID:10002821-1698852600-1698856200@cmsa.fas.harvard.edu
SUMMARY:Universality of max-margin classifiers
DESCRIPTION:Probability Seminar \nSpeaker: Youngtak Sohn (MIT) \nTitle: Universality of max-margin classifiers \nAbstract: Many modern learning methods\, such as deep neural networks\, are so complex that they perfectly fit the training data. Despite this\, they generalize well to the unseen data. Motivated by this phenomenon\, we consider high-dimensional binary classification with linearly separable data. First\, we consider Gaussian covariates and characterize linear classification problems for which the minimum norm interpolating prediction rule\, namely the max-margin classification\, has near-optimal prediction accuracy. Then\, we discuss universality of max-margin classification. In particular\, we characterize the prediction accuracy of the non-linear random features model\, a two-layer neural network with random first layer weights. The spectrum of the kernel random matrices plays a crucial role in the analysis. Finally\, we consider the wide-network limit\, where the number of neurons tends to infinity\, and show how non-linear max-margin classification with random features collapse to a linear classifier with a soft-margin objective. \nJoint work with Andrea Montanari\, Feng Ruan\, Jun Yan\, and Basil Saeed.
URL:https://cmsa.fas.harvard.edu/event/probability-11123/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Probability Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Probability-Seminar-11.01.23.png
END:VEVENT
END:VCALENDAR