Don't Get Your Kroneckers in a Twist: Gaussian Processes on High-Dimensional Incomplete Grids

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Højlund, Mads Greisen, Lykke-Møller, August Smart, Moss, Henry, Christiansen, Ove
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911663192539136
author Højlund, Mads Greisen
Lykke-Møller, August Smart
Moss, Henry
Christiansen, Ove
author_facet Højlund, Mads Greisen
Lykke-Møller, August Smart
Moss, Henry
Christiansen, Ove
contents We introduce CUTS-GPR, a new method for performing numerically exact Gaussian process regression (GPR) in high-dimensional settings. The key component of CUTS-GPR is an extremely fast kernel matrix-vector product, which exhibits near-linear or even linear scaling with the amount of training data, $N$, and low-order polynomial scaling with dimensionality, $D$. This is obtained by combining an additive kernel with an incomplete grid and exploiting the resulting structure of the kernel matrix. We demonstrate the scalability of the matrix-vector product by running benchmarks with billions of data points and thousands of dimensions. Full GPR calculations, including hyperparameter optimization, are completed in a matter of hours for $N = 447 265$ and $D = 24$. We demonstrate that our CUTS-GPR enables Bayesian modeling of high-dimensional potential energy surfaces - a longstanding challenge in computational chemistry.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08036
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Don't Get Your Kroneckers in a Twist: Gaussian Processes on High-Dimensional Incomplete Grids
Højlund, Mads Greisen
Lykke-Møller, August Smart
Moss, Henry
Christiansen, Ove
Machine Learning
We introduce CUTS-GPR, a new method for performing numerically exact Gaussian process regression (GPR) in high-dimensional settings. The key component of CUTS-GPR is an extremely fast kernel matrix-vector product, which exhibits near-linear or even linear scaling with the amount of training data, $N$, and low-order polynomial scaling with dimensionality, $D$. This is obtained by combining an additive kernel with an incomplete grid and exploiting the resulting structure of the kernel matrix. We demonstrate the scalability of the matrix-vector product by running benchmarks with billions of data points and thousands of dimensions. Full GPR calculations, including hyperparameter optimization, are completed in a matter of hours for $N = 447 265$ and $D = 24$. We demonstrate that our CUTS-GPR enables Bayesian modeling of high-dimensional potential energy surfaces - a longstanding challenge in computational chemistry.
title Don't Get Your Kroneckers in a Twist: Gaussian Processes on High-Dimensional Incomplete Grids
topic Machine Learning
url https://arxiv.org/abs/2605.08036