BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Shrinkage Estimation in High Dimensions - Dr K. Pavan Srinath\, CU
 ED
DTSTART:20160602T140000Z
DTEND:20160602T150000Z
UID:TALK65819@talks.cam.ac.uk
CONTACT:Prof. Ramji Venkataramanan
DESCRIPTION:We consider the problem of estimating a high-dimensional vecto
 r of parameters from a noisy one-time observation. The noise vector is iid
  Gaussian with known variance\, and the performance of the estimator is me
 asured via squared-error loss. For this problem\, _shrinkage estimators_\,
  which shrink the observed data towards a point or a target subspace\, hav
 e evoked a lot of interest because they dominate the simple maximum-likeli
 hood estimator (when the number of dimensions exceeds two). \n\nIn this ta
 lk\, we first review the key aspects of shrinkage estimation\, and then in
 troduce shrinkage estimators that use the data to determine a "good" targe
 t subspace to shrink the data towards. We give concentration results for t
 he squared-error loss and convergence results for the risk of the proposed
  estimators. We also present simulation results that validate the theory. 
 \n\nThis is joint work with Ramji Venkataramanan.
LOCATION:LR6\, Department of Engineering
END:VEVENT
END:VCALENDAR