GPfit: An R package for Gaussian Process Model Fitting using a New Optimization Algorithm

Abstract

Gaussian process (GP) models are commonly used statistical metamodels for emulating expensive computer simulators. Fitting a GP model can be numerically unstable if any pair of design points in the input space are close together. Ranjan, Haynes, and Karsten (2011) proposed a computationally stable approach for fitting GP models to deterministic computer simulators. They used a genetic algorithm based approach that is robust but computationally intensive for maximizing the likelihood. This paper implements a slightly modified version of the model proposed by Ranjan et al. (2011), as the new R package GPfit. A novel parameterization of the spatial correlation function and a new multi-start gradient based optimization algorithm yield optimization that is robust and typically faster than the genetic algorithm based approach. We present two examples with R codes to illustrate the usage of the main functions in GPfit. Several test functions are used for performance comparison with a popular R package mlegp. GPfit is a free software and distributed under the general public license, as part of the R software project (R Development Core Team 2012).

20 pages, 17 images

Cited by in corpus (21)

• Bayesian uncertainty analysis for complex systems biology models: emulation, global parameter searches and evaluation of gene functions
• Calibrating a large computer experiment simulating radiative shock hydrodynamics
• Deterministic Sampling of Expensive Posteriors Using Minimum Energy Designs
• The origin of the late-time luminosity of supernova 2011dh
• Parallelizing Gaussian Process Calculations in R
• RobustGaSP: Robust Gaussian Stochastic Process Emulation in R
• Bayesian test of the mass of the graviton with planetary ephemerides
• A History Matching Approach for Calibrating Hydrological Models
• Mixture-based Multiple Imputation Model for Clinical Data with a Temporal Dimension
• Population Quasi-Monte Carlo
• A Comparative Tutorial of Bayesian Sequential Design and Reinforcement Learning
• Gaussian Processes for Traffic Speed Prediction at Different Aggregation Levels
• iprior: An R Package for Regression Modelling using I-priors
• Statistical Modelling and Analysis of the Computer-Simulated Datasets
• Testing the mass of the graviton with Bayesian planetary numerical ephemerides B-INPOP
• Kernel-smoothed proper orthogonal decomposition (KSPOD)-based emulation for prediction of spatiotemporally evolving flow dynamics
• Efficient Emulation of Computer Models Utilising Multiple Known Boundaries of Differing Dimensions
• Inverse problem for time-series valued computer model via scalarization
• Inverse Problem for Dynamic Computer Simulators via Multiple Scalar-valued Contour Estimation
• Efficient Optimization of the Likelihood Function in Gaussian Process Modelling
• Understanding Hormonal Crosstalk in Arabidopsis Root Development via Emulation and History Matching