BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.19//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
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:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20181104T060000
END:STANDARD
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
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190917T110000
DTEND;TZID=America/New_York:20190917T120000
DTSTAMP:20260408T131936
CREATED:20190806T151855Z
LAST-MODIFIED:20190806T151855Z
UID:1788-1568718000-1568721600@seasevents.nmsdev7.com
SUMMARY:ESE & Statistics Seminar: "Large Neural Networks: Insights from Linearized Models"
DESCRIPTION:Abstract: Modern machine learning models\, and in particular multilayer neural networks\, exhibit a broad range of puzzling phenomena. Their training requires to minimize a highly non-convex high-dimensional cost function\, and yet it is efficiently addressed using simple gradient descent (GD) or stochastic gradient descent (SGD) algorithms. This model contains more parameters than the number of samples\, and indeed they often are able to achieve zero training error\, i.e. to perfectly interpolate or classify the training data. In fact\, they can achieve zero training error even if the true labels are replaced by random ones.  Despite this fact\, they can generalize well beyond the training set. Finally\, far from being a nuisance or limitation\, this massive over parameterization appears to play an important role in explaining the power of these models. \nI will discuss these phenomena\, and how we can make sense of them by using some simple linear models. Finally\, I will discuss the limitations of these `linear explanations’\, and open challenges.\n[Based on joint work with: Behrooz Ghorbani\, Song Mei\, Theodor Misiakiewicz\, and with Ryan Tibshirani\, Saharon Rosset\, Trevor Hastie]
URL:https://seasevents.nmsdev7.com/event/ese-seminar-andrea-montanari/
LOCATION:PICS Conference Room 534 – A Wing \, 5th Floor\, 3401 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
END:VCALENDAR