Activity Number:
|
97
|
Type:
|
Topic Contributed
|
Date/Time:
|
Monday, July 30, 2007 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Bayesian Statistical Science
|
Abstract - #309645 |
Title:
|
Pattern Search Optimization with a Treed Gaussian Process Oracle
|
Author(s):
|
Matthew Taddy*+ and Genetha A. Gray and Herbert Lee and Robert Gramacy and Monica Martinez-Canales
|
Companies:
|
University of California, Santa Cruz and Sandia National Laboratories and University of California, Santa Cruz and University of Cambridge and Sandia National Laboratories
|
Address:
|
SOE Grads UCSC, Santa Cruz, CA, 95060,
|
Keywords:
|
optimization ; expected improvement ; convergence ; partitioning ; Gaussian process
|
Abstract:
|
This work combines pattern search optimization with a statistical emulator based on Treed Gaussian Processes (TGP) to create a new hybrid algorithm. The goal is to use the global probabilistic view provided by TGP to inform the local pattern search and derive a more intelligent optimization algorithm. We also propose ways in which the emulator can be used to gain information about the objective function, inform the algorithm stopping rules and provide a probabilistic analysis of the type of convergence. We present the algorithm, a framework for statistically informed optimization, and illustrate the work with numerical results.
|