Nested Kriging predictions for datasets with large number of observations

2016/07/19 by Didier Rullière, Rullière, Didier, Nicolas Durrande +5 · 1 citation
Computer Science · Decision Sciences · #Advanced Multi-Objective Optimization Algorithms #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (stat.ML) #Optimal Experimental Design Methods

paper · doi:10.48550/arxiv.1607.05432

openalex publication_date 2016/07/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This work falls within the context of predicting the value of a real function at some input locations given a limited number of observations of this function. The Kriging interpolation technique (or Gaussian process regression) is often considered to tackle such a problem but the method suffers from its computational burden when the number of observation points is large. We introduce in this article nested Kriging predictors which are constructed by aggregating sub-models based on subsets of observation points. This approach is proven to have better theoretical properties than other aggregation methods that can be found in the literature. Contrarily to some other methods it can be shown that the proposed aggregation method is consistent. Finally, the practical interest of the proposed method is illustrated on simulated datasets and on an industrial test case with 10⁴ observations in a 6-dimensional space.

Citations

• Training Products of Experts by Minimizing Contrastive Divergence

Cited by

• Operator Learning at Machine Precision

Related

• Properties and comparison of some Kriging sub-model aggregation methods
• On Prediction Properties of Kriging: Uniform Error Bounds and Robustness
• Patchwork Kriging for Large-scale Gaussian Process Regression
• Explaining and Connecting Kriging with Gaussian Process Regression
• Cluster-based Kriging Approximation Algorithms for Complexity Reduction