|
Title |
Adaptive Parameter Space Exploration with Gaussian Process Trees
|
| Speaker |
Herb Lee
University of California, Santa Cruz
herbie@ams.ucsc.edu |
| Date |
Wednesday, April 6, 2005 |
| Time |
10-11am (PT)
11-12am (MT)
|
| Location |
Bldg. 915, Room S101 (Sandia - CA)
Bldg. 980, Room 24 (Sandia - NM)
|
|
Abstract |
Traditionally, to obtain even a qualitative understanding of
the output of a computer simulation, runs have been made over a
complete grid of input parameter configurations. For large
scale simulations, such sweeps can be prohibitively expensive,
and fixed designs such as Latin hypercubes can be still
difficult yet inefficient. Thus, there is a need for
computationally inexpensive surrogate models that can be used
in place of simulation to adaptively select new settings of
input parameters and map the response with far fewer simulation
runs. We provide a general methodology for modeling and
adaptive sampling to greatly speed up parameter sweeps. Binary
trees are used to recursively partition the input space, and
Gaussian process models are fit within each partition. Trees
facilitate non-stationarity and a Bayesian interpretation
provides a measure of uncertainty in the sample space which can
be used to guide future sampling. Our methods are illustrated
on several examples, including the motivating example involving
computational fluid dynamics simulation of a NASA reentry
vehicle.
|
|
About the Speaker |
Herbert Lee is an assistant professor in the Department of
Applied Mathematics and Statistics at the University of
California, Santa Cruz. He completed his PhD in statistics at
Carnegie Mellon University and did a post-doc at Duke
University. His primary research interests are spatial
statistics (applied to computer experiments, inverse problems,
and environmental applications) and machine learning
(investigating the foundational connections between statistics
and machine learning).
|
| Host: |
Genetha Gray, gagray@sandia.gov, (925) 294-4957
|
This seminar series is hosted by the Computational Sciences and
Mathematics Research Department at Sandia National Labs in
Livermore, CA.
This seminar is funded by the Computer Science Research
Institute (CSRI).
To schedule a time to meet with the speaker before or after the talk,
please make arrangements with the host listed above.
Visitors from outside Sandia require at least 3 days notice in order
to attend. For more information, see http://csmr.ca.sandia.gov/csri/visitor.html.
The exception is any U.S. Citizens with a valid DOE badge.
Alternatively, have the badge activated for site
access by going to the badge office in building 911.
|
