Local Gaussian Process Model for Large-scale Dynamic Computer Experiments

TL;DR

This paper introduces a computationally efficient local Gaussian process emulator for large-scale dynamic computer experiments, using local neighborhoods and SVD-based GP models to handle time series outputs effectively.

Contribution

It proposes a novel local neighborhood selection criterion and combines SVD with Gaussian processes for scalable emulation of dynamic simulators.

Findings

Outperforms naive Euclidean distance-based local methods

Effective on test functions and real-life applications

Reduces computational complexity for large-scale dynamic models

Abstract

The recent accelerated growth in the computing power has generated popularization of experimentation with dynamic computer models in various physical and engineering applications. Despite the extensive statistical research in computer experiments, most of the focus had been on the theoretical and algorithmic innovations for the design and analysis of computer models with scalar responses. In this paper, we propose a computationally efficient statistical emulator for a large-scale dynamic computer simulator (i.e., simulator which gives time series outputs). The main idea is to first find a good local neighbourhood for every input location, and then emulate the simulator output via a singular value decomposition (SVD) based Gaussian process (GP) model. We develop a new design criterion for sequentially finding this local neighbourhood set of training points. Several test functions and a real-life application have been used to demonstrate the performance of the proposed approach over a naive method of choosing local neighbourhood set using the Euclidean distance among design points.