BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Spectral estimation for a class of high-dimensional linear process
 es - Debashis Paul (University of California\, Davis)
DTSTART:20180322T143000Z
DTEND:20180322T153000Z
UID:TALK102799@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:We present results about the limiting behavior of the empirica
 l distribution of eigenvalues of weighted integrals of the sample periodog
 ram for a class of high-dimensional linear processes. The processes under 
 consideration are characterized by having simultaneously diagonalizable co
 efficient matrices.   We make use of these asymptotic results\, derived un
 der the setting where the dimension and sample size are comparable\, to fo
 rmulate an estimation strategy for the distribution of eigenvalues of the 
 coefficients of the linear process. This approach generalizes existing wor
 ks on estimation of the spectrum of an unknown covariance matrix for high-
 dimensional i.i.d.  observations.  &nbsp\; <br><br>(Joint work with Jamshi
 d Namdari and Alexander Aue)<br><br><br><br>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR