A Residual Tree Gaussian Process Modeling Framework for High-Dimensional Data
Abstract
With the advance of measurement technologies and increasing computing power, large spatial data with heterogeneous structures are often collected over high-dimensional domains. Existing Gaussian process (GP) models and computational strategies are often inadequate for analyzing such datasets in multi-dimensional domains. To address these challenges, we develop a Bayesian residual tree GP methodology called ResTGP for large spatial data with potentially heterogeneous structures in multi-dimensional domains. The key idea is to decompose a Gaussian process at a cascade of resolutions along a dyadic tree through iteratively computing predictive and residual processes so that the residual process on each tree node, both interior and leaf, becomes sufficient for the finer-level dependency within that node. This allows characterization of the underlying covariance structure in a flexible, multi-scale manner while achieving divide-and-conquer on the data domain, which leads to computational efficiency. To allow efficient tree inference, we introduce a computational strategy for Bayesian inference based on recursive message passing, which scales linearly with the sample size given the tree. This paper also proves posterior consistency of the model for estimating continuous functions in a nonparametric regression framework. Extensive numerical examples and the storm surge application confirm the advantages of the proposed method.
Related
- Gaussian-process surrogate indicators for residual-based adaptive GMsFEM
- Gaussian Process Modeling of Time Series
- Efficient Gaussian Process Modeling for Large Replicated and Censored Data in Industrial Research
- Triply-Scalable Equivariant Gaussian Process Modeling
- Bezier-GP: Bezier-Surface-Based Gaussian Process for Chips-on-Wafer Warpage Modeling
BibTeX
@misc{ma2026residual,
title = {{A Residual Tree Gaussian Process Modeling Framework for High-Dimensional Data}},
author = {Pulong Ma and Li Ma},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.02893},
eprint = {2610.02893},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.02893},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Residual Tree Gaussian Process Modeling Framework for High-Dimensional Data
AU - Pulong Ma
AU - Li Ma
PY - 2026
DA - 2026/10/02
PB - arXiv
DO - 10.48550/arxiv.2610.02893
UR - https://arxiv.org/abs/2610.02893
AB - With the advance of measurement technologies and increasing computing power, large spatial data with heterogeneous structures are often collected over high-dimensional domains. Existing Gaussian process (GP) models and computational strategies are often inadequate for analyzing such datasets in multi-dimensional domains. To address these challenges, we develop a Bayesian residual tree GP methodology called ResTGP for large spatial data with potentially heterogeneous structures in multi-dimensional domains. The key idea is to decompose a Gaussian process at a cascade of resolutions along a dyadic tree through iteratively computing predictive and residual processes so that the residual process on each tree node, both interior and leaf, becomes sufficient for the finer-level dependency within that node. This allows characterization of the underlying covariance structure in a flexible, multi-scale manner while achieving divide-and-conquer on the data domain, which leads to computational efficiency. To allow efficient tree inference, we introduce a computational strategy for Bayesian inference based on recursive message passing, which scales linearly with the sample size given the tree. This paper also proves posterior consistency of the model for estimating continuous functions in a nonparametric regression framework. Extensive numerical examples and the storm surge application confirm the advantages of the proposed method.
ER -