Exploiting Variance Reduction Potential in Local Gaussian Process Search
From MaRDI portal
Abstract: Gaussian process models are commonly used as emulators for computer experiments. However, developing a Gaussian process emulator can be computationally prohibitive when the number of experimental samples is even moderately large. Local Gaussian process approximation (Gramacy and Apley, 2015) was proposed as an accurate and computationally feasible emulation alternative. However, constructing local sub-designs specific to predictions at a particular location of interest remains a substantial computational bottleneck to the technique. In this paper, two computationally efficient neighborhood search limiting techniques are proposed, a maximum distance method and a feature approximation method. Two examples demonstrate that the proposed methods indeed save substantial computation while retaining emulation accuracy.
Recommendations
- Combined Global and Local Search for Optimization with Gaussian Process Models
- Using Gaussian processes for variance reduction in policy gradient algorithms
- Gaussian variable neighborhood search for continuous optimization
- An analysis of covariance parameters in Gaussian process-based optimization
- Local Gaussian Process Model for Large-Scale Dynamic Computer Experiments
- scientific article; zbMATH DE number 4174178
- Deterministic global optimization with Gaussian processes embedded
- Local optimization-based statistical inference
- Locally induced Gaussian processes for large-scale simulation experiments
Cited in
(12)- Multiresolution functional ANOVA for large-scale, many-input computer experiments
- A generalized Gaussian process model for computer experiments with binary time series
- Efficient optimization of the likelihood function in Gaussian process modelling
- Composite Gaussian process models for emulating expensive functions
- Locally induced Gaussian processes for large-scale simulation experiments
- Clustered active-subspace based local Gaussian process emulator for high-dimensional and complex computer models
- Using Gaussian processes for variance reduction in policy gradient algorithms
- An efficient surrogate model for emulation and physics extraction of large eddy simulations
- Emulating satellite drag from large simulation experiments
- Cross-validation-based adaptive sampling for Gaussian process models
- scientific article; zbMATH DE number 7650422 (Why is no real title available?)
- Predictive Subdata Selection for Computer Models
This page was built for publication: Exploiting Variance Reduction Potential in Local Gaussian Process Search
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4639563)
