Online Program Home
  My Program

Abstract Details

Activity Number: 168 - Bayesian Models for Gaussian and Point Processes
Type: Contributed
Date/Time: Monday, July 31, 2017 : 10:30 AM to 12:20 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #324899 View Presentation
Title: Nonseparable Gaussian Stochastic Process: a Unified View and Computational Strategy
Author(s): Mengyang Gu* and Yanxun Xu and Barbara Engelhardt
Companies: Johns Hopkins University and Johns Hopkins University and Princeton University
Keywords: Gaussian Process ; functional data ; fast computation ; exact algorithm ; nonseparable covariance ; Bayesian analysis
Abstract:

We introduce a general framework of Gaussian stochastic process (GaSP) models to capture multiple functional data observations with a fast, exact algorithm in large-scale data. GaSP models are widely used in modeling functional data, with applications in emulation, interpolation, classification, and uncertainty quantification. While GaSP is flexible from a modeling standpoint, the major limitation is in the evaluation of the likelihood, which is O(n^3), where n is the sample size. We propose a general class of nonseparable GaSP models, in which the computation is linear to the sample size and the evaluation of the likelihood is exact, i.e. without assuming that either the covariance or precision matrices is sparse or low-rank. We show that linear regression and separable GaSP models are special cases of the proposed nonseparable GaSP. The advantages of our nonseparable GaSP model with objective Bayesian analysis are illustrated in an epigenetic application in which the goal is to interpolate unobserved methylation levels.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association