BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Spectral estimation for a class of high-dimensiona
l linear processes - Debashis Paul (University of
California\, Davis)
DTSTART;TZID=Europe/London:20180322T143000
DTEND;TZID=Europe/London:20180322T153000
UID:TALK102802AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/102802
DESCRIPTION:We present results about the limiting behavior of
the empirical distribution of eigenvalues of weigh
ted integrals of the sample periodogram for a clas
s of high-dimensional linear processes. The proces
ses under consideration are characterized by havin
g simultaneously diagonalizable coefficient matric
es. We make use of these asymptotic results\, de
rived under the setting where the dimension and sa
mple size are comparable\, to formulate an estimat
ion strategy for the distribution of eigenvalues o
f the coefficients of the linear process. This app
roach generalizes existing works on estimation of
the spectrum of an unknown covariance matrix for h
igh-dimensional i.i.d. observations.  \;
(Joint work with Jamshid Namdari and Alexande
r Aue)
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR