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: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:20230503T153000
DTEND;TZID=America/New_York:20230503T163000
DTSTAMP:20240111T083748Z
CREATED:20230808T175916Z
LAST-MODIFIED:20240111T083748Z
UID:10001198-1683127800-1683131400@cmsa.fas.harvard.edu
SUMMARY:Random Neural Networks
DESCRIPTION:Probability Seminar \nSpeaker: Boris Hanin (Princeton)\n\nTitle: Random Neural Networks \nAbstract: Fully connected neural networks are described two by structural parameters: a depth L and a width N. In this talk\, I will present results and open questions about the asymptotic analysis of such networks with random weights and biases in the regime where N (and potentially L) are large. The first set of results are for deep linear networks\, which are simply products of L random matrices of size N x N. I’ll explain how the setting where the ratio L / N is fixed with both N and L large reveals a number of phenomena not present when only one of them is large. I will then state several results about non-linear networks in which this depth-to-width ratio L / N again plays a crucial role and gives an effective notion of depth for a random neural network.
URL:https://cmsa.fas.harvard.edu/event/probability-5323/
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-05.03.23.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230511T133000
DTEND;TZID=America/New_York:20230511T143000
DTSTAMP:20240111T084858Z
CREATED:20230808T180145Z
LAST-MODIFIED:20240111T084858Z
UID:10001199-1683811800-1683815400@cmsa.fas.harvard.edu
SUMMARY:How do the eigenvalues of a large non-Hermitian random matrix behave?
DESCRIPTION:Probability Seminar \nSpeaker: Giorgio Cipolloni (Princeton) \nTitle: How do the eigenvalues of a large non-Hermitian random matrix behave? \nAbstract: We prove that the fluctuations of the eigenvalues converge to the Gaussian Free Field (GFF) on the unit disk. These fluctuations appear on a non-natural scale\, due to strong correlations between the eigenvalues. Then\, motivated by the long time behaviour of the ODE \dot{u}=Xu\, we give a precise estimate on the eigenvalue with the largest real part and on the spectral radius of X. \nLocation: Science Center Room 232
URL:https://cmsa.fas.harvard.edu/event/probability-51123/
LOCATION:Harvard Science Center\, 1 Oxford Street\, Cambridge\, MA\, 02138
CATEGORIES:Probability Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Probability-Seminar-05.11.23.png
END:VEVENT
END:VCALENDAR