Abstract Details
Activity Number:
|
477
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, August 6, 2014 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics and the Environment
|
Abstract #310864
|
|
Title:
|
Distributed Gaussian Process for Massive Spatial Data
|
Author(s):
|
Rajarshi Guhaniyogi*+ and Natesh S. Pillai and Sudipto Banerjee
|
Companies:
|
Duke University and Harvard and University of Minnesota
|
Keywords:
|
Gaussian Process ;
Infill Aysmptotics ;
Meta Analysis ;
Massive Spatial Data ;
Low Rank ;
Predictive Process
|
Abstract:
|
Large point referenced datasets occur frequently in the environmental and natural sciences. Use of Bayesian hierarchical spatial models for analyzing these datasets is undermined by onerous computational burdens associated with parameter estimation. Low-rank spatial process models attempt to resolve this problem by projecting spatial effects to a lower-dimensional subspace. However, accurate estimation of low rank basis functions often hinders them to scale more than 50000 sample size with manageable computation time. Motivated by the idea of meta analysis, we propose distributed Gaussian process approach that facilitates storage and computation of massive spatial data. Distributed Gaussian process is found to yield satisfactory inference extremely fast even with millions of data. The proposed method has also found to have strong theoretical support. Practical performance is illustrated through a number simulation studies and real life examples.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.