RAND Statistics Seminar Series

Treed Gaussian Processes and Limiting Linear Models, with applications to Computer Experiments

Presented by Herbie Lee, UCSC Department of Applied Math and Statistics
Thursday, October 5, 2006
RAND Corporation, Santa Monica, CA
Please contact Stephanie Thomas if you would like to attend this seminar.

Abstract

Gaussian processes are a flexible model useful for a wide variety of applications, including the modeling of computer simulation experiments. Gaussian processes retain the linear model either as a special case, or in the limit. We show how this relationship can be exploited when the data are at least partially linear. Linearity can be extracted on a per-dimension basis, and can be combined with treed partition models to yield a highly efficient nonstationary model. A fully Bayesian approach allows complete estimation of uncertainty, which can then be used for adaptively updating experimental designs. We demonstrate our methods on several synthetic and real datasets of varying linearity and dimensionality, including our motivating example of the adaptive design of a simulation experiment for learning the response surface of flight characteristics of a proposed rocket booster.



Attending a Seminar

RAND Visitors are welcome to attend the statistics seminars, but must RSVP at least one day prior to the seminar. To ensure your attendance, contact Stephanie Thomas at sjthomas@rand.org with your name, company or university affiliation, and national citizenship (for security purposes). Light refreshments will be served.

For directions to RAND see: http://www.rand.org/about/locations/santa-monica.html
Visitors must enter through the north-parking garage, which is accessible from Main Street in our new office building. Inform the attendant that you are there for the Statistics Seminar Series and you will be directed to the appropriate parking area. If there is no attendant present, use the intercom and tell them that you are here for the Statistics Seminar Series. After parking, follow the instructions to the appropriate conference area. (1776 Main Street)

Reminder: the old RAND surface parking lots have been permanently closed.

For further information and to be added to the mailing list contact Stephanie Thomas at sjthomas@rand.org.