Statistics Seminars: Small Sample Bayesian Designs for Complex High-Dimensional Models Based on Information Gained Using Fast Approximations
12 October 2009 14:15 in CM221
We consider the problem of designing for complex high-dimensional computer models which can be evaluated at different levels of accuracy. Ordinarily, this requires performing many expensive evaluations of the most accurate version of the computer model in order to obtain a reasonable coverage of the design space. In some cases, it is possible to supplement the information from the accurate model evaluations with a large number of evaluations of a cheap, approximate version of the computer model to enable a more informed design choice. We describe an approach which combines the information from both the approximate model and the accurate model into a single multiscale emulator for the computer model. We then propose a design strategy for the selection of a small number of expensive evaluations of the accurate computer model based on our multiscale emulator and a decomposition of the input parameter space. The methodology is illustrated with an example concerning a computer simulation of a hydrocarbon reservoir.
Contact firstname.lastname@example.org for more information