BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.4.8//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:346@fds.yale.edu
DTSTART;TZID=America/New_York:20240306T113000
DTEND;TZID=America/New_York:20240306T130000
DTSTAMP:20240426T145946Z
URL:https://fds.yale.edu/events/fds-colloquium-ankur-moitra-mit-learning-f
rom-dynamics/
SUMMARY:FDS Colloquium: Ankur Moitra (MIT) "Learning from Dynamics"
DESCRIPTION:\nAbstract: Linear dynamical systems are the canonical model
for time series data. They have wide-ranging applications and there is a
vast literature on learning their parameters from input-output sequences.
Moreover they have received renewed interest because of their connections
to recurrent neural networks.\n\n\n\nBut there are wide gaps in our unders
tanding. Existing works have only asymptotic guarantees or else make restr
ictive assumptions\, e.g. that preclude having any long-range correlations
. In this work\, we give a new algorithm based on the method of moments th
at is computationally efficient and works under essentially minimal assump
tions. Our work points to several missed connections\, whereby tools from
theoretical machine learning including tensor methods\, can be used in non
-stationary settings.\n\n\n\nBio: \;Ankur Moitra is a theoretical comp
uter scientist\, and a major goal in his work is to give algorithms with p
rovable guarantees for various problems in machine learning. He is a membe
r of the Theory of Computation group\, MachineLearning@MIT\, Foundations o
f Data Science and the Center for Statistics.\n\n\n\nWebsite: \;https:
//people.csail.mit.edu/moitra/\n
CATEGORIES:Colloquium,Seminar Series,Statistics & Data Science Seminar
LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th
Floor\, Room 1327\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro
om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL
E=Yale Institute for Foundations of Data Science:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR