Properties and comparison of some kriging sub-model aggregation methods
From MaRDI portal
Publication:2676512
Abstract: Kriging is a widely employed technique, in particular for computer experiments, in machine learning or in geostatistics. An important challenge for Kriging is the computational burden when the data set is large. This article focuses on a class of methods aiming at decreasing this computational cost, consisting in aggregating Kriging predictors based on smaller data subsets. It proves that aggregation methods that ignore the covariancebetween sub-models can yield an inconsistent final Kriging prediction. In contrast, a theoretical study of the nested Kriging method shows additional attractive properties for it: First, this predictor is consistent, second it can be interpreted as an exact conditional distribution for a modified process and third, the conditional covariances given the observations can be computed efficiently. This article also includes a theoretical and numerical analysis of how the assignment of the observation points to the sub-models can affect the prediction ability of the aggregated model. Finally, the nested Kriging method is extended to measurement errors and to universal Kriging.
Recommendations
- Nested kriging predictions for datasets with a large number of observations
- Penalized blind kriging in computer experiments
- Subset selection from large datasets for kriging modeling
- Kriging metamodeling in simulation: a review
- A note on the choice and the estimation of kriging models for the analysis of deterministic computer experiments
Cites work
- A case study competition among methods for analyzing large spatial data
- A unifying view of sparse approximate Gaussian process regression
- Asymptotic properties of a maximum likelihood estimator with data from a Gaussian process
- Convergence properties of the expected improvement algorithm with fixed mean and covariance functions
- Covariance tapering for likelihood-based estimation in large spatial data sets
- Cross validation and maximum likelihood estimations of hyper-parameters of Gaussian processes with model misspecification
- Cross-validation estimation of covariance parameters under fixed-domain asymptotics
- Development and evaluation of geostatistical methods for non-Euclidean-based spatial covariance matrices
- Efficient global optimization of expensive black-box functions
- Fixed Rank Kriging for Very Large Spatial Data Sets
- Gaussian Markov Random Fields
- Gaussian Predictive Process Models for Large Spatial Data Sets
- Gaussian processes for machine learning.
- Geostatistics. Modeling spatial uncertainty.
- Improving the performance of predictive process modeling for large datasets
- Nested kriging predictions for datasets with a large number of observations
- On the effect of covariance function estimation on the accuracy of kriging predictors
- Probability aggregation methods in geoscience
- Statistics for spatial data
- The origins of kriging
- Training Products of Experts by Minimizing Contrastive Divergence
Cited in
(5)
This page was built for publication: Properties and comparison of some kriging sub-model aggregation methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2676512)
