A Global-Local Approximation Framework for Large-Scale Gaussian Process Modeling
This addresses computational efficiency for large-scale Gaussian process modeling, which is incremental as it builds on existing global and local approximation methods.
The authors tackled the computational bottleneck in large-scale Gaussian process modeling by proposing TwinGP, a combined global-local approximation framework that uses subsets of data points and kernels. The method achieved performance on par or better than state-of-the-art GP methods at a fraction of their computational cost.
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.