A Global-Local Approximation Framework for Large-Scale Gaussian Process Modeling

Abstract

In this work, we propose a novel framework for large-scale Gaussian process (GP) modeling. Contrary to the global, and local approximations proposed in the literature to address the computational bottleneck with exact GP modeling, we employ a combined global-local approach in building the approximation. Our framework uses a subset-of-data approach where the subset is a union of a set of global points designed to capture the global trend in the data, and a set of local points specific to a given testing location to capture the local trend around the testing location. The correlation function is also modeled as a combination of a global, and a local kernel. The performance of our framework, which we refer to as TwinGP, is on par or better than the state-of-the-art GP modeling methods at a fraction of their computational cost.

References in corpus (10)

• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
• Scalable Variational Gaussian Process Classification
• SPlit: An Optimal Method for Data Splitting
• Composite Gaussian process models for emulating expensive functions
• Efficient emulators of computer experiments using compactly supported correlation functions, with an application to cosmology
• A Framework for Evaluating Approximation Methods for Gaussian Process Regression
• Data Twinning
• Modelling local and global phenomena with sparse Gaussian processes
• Patchwork Kriging for Large-scale Gaussian Process Regression
• Numerical issues in maximum likelihood parameter estimation for Gaussian process interpolation

Cited by in corpus (1)

• Sequential Designs for Filling Output Spaces