BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.17.1//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: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:20201014T150000
DTEND;TZID=America/New_York:20201014T160000
DTSTAMP:20240515T192014Z
CREATED:20240201T021720Z
LAST-MODIFIED:20240515T192014Z
UID:10001522-1602687600-1602691200@cmsa.fas.harvard.edu
SUMMARY:Triple Descent and a Fine-Grained Bias-Variance Decomposition
DESCRIPTION:Speaker: Jeffrey Pennington\, Google Brain \nTitle: Triple Descent and a Fine-Grained Bias-Variance Decomposition \nAbstract: Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity\, striking a balance between simpler models that exhibit high bias and more complex models that exhibit high variance of the predictive function. However\, such a simple trade-off does not adequately describe the behavior of many modern deep learning models\, which simultaneously attain low bias and low variance in the heavily overparameterized regime. Recent efforts to explain this phenomenon theoretically have focused on simple settings\, such as linear regression or kernel regression with unstructured random features\, which are too coarse to reveal important nuances of actual neural networks. In this talk\, I will describe a precise high-dimensional asymptotic analysis of Neural Tangent Kernel regression that reveals some of these nuances\, including non-monotonic behavior deep in the overparameterized regime. I will also present a novel bias-variance decomposition that unambiguously attributes these surprising observations to particular sources of randomness in the training procedure.
URL:https://cmsa.fas.harvard.edu/event/10-14-2020-new-technologies-seminar/
LOCATION:MA
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-New-Technologies-in-Mathematics-10.14.20.png
END:VEVENT
END:VCALENDAR