BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Partial least squares for dependent data - Tatyana Krivobokova (Ge
 org-August-Universität Göttingen)
DTSTART:20180510T100000Z
DTEND:20180510T110000Z
UID:TALK105403@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>We consider the linear and kernel partial least squares 
 algorithms for dependent data and study the consequences of ignoring the d
 ependence both theoretically and numerically. For linear partial least squ
 ares estimator we derive convergence rates and show that ignoring non-stat
 ionary dependence structures can lead to inconsistent estimation. For kern
 el partial least squares estimator we establish convergence rates under a 
 source and an effective dimensionality conditions. It is shown both theore
 tically and in simulations that long range dependence results in slower co
 nvergence rates. A protein dynamics example illustrates our results and sh
 ows high predictive power of partial least squares.<br> This is joint work
  with Marco Singer\, Axel Munk and Bert de Groot.</span><br><br><br><br>
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR