Cases for the nugget in modeling computer experiments
From MaRDI portal
Publication:693296
Abstract: Most surrogate models for computer experiments are interpolators, and the most common interpolator is a Gaussian process (GP) that deliberately omits a small-scale (measurement) error term called the nugget. The explanation is that computer experiments are, by definition, "deterministic", and so there is no measurement error. We think this is too narrow a focus for a computer experiment and a statistically inefficient way to model them. We show that estimating a (non-zero) nugget can lead to surrogate models with better statistical properties, such as predictive accuracy and coverage, in a variety of common situations.
Recommendations
- The effect of the nugget on Gaussian process emulators of computer models
- Design and analysis of computer experiments. With comments and a rejoinder by the authors
- Analysis methods for computer experiments: how to assess and what counts?
- On estimation of surrogate models for multivariate computer experiments
- Methods for design and analysis of computer experiments
Cites work
- scientific article; zbMATH DE number 1522715 (Why is no real title available?)
- Bayesian calibration of computer models. (With discussion)
- Bayesian emulation and calibration of a stochastic computer model of mitochondrial DNA deletions in substantia nigra neurons
- Bayesian treed Gaussian process models with an application to computer modeling
- Design and analysis of computer experiments. With comments and a rejoinder by the authors
- Gaussian processes and limiting linear models
- Interpolation of spatial data. Some theory for kriging
- Microcolony and biofilm formation as a survival strategy for bacteria
- Multivariate adaptive regression splines
- On the condition number of covariance matrices in kriging, estimation, and simulation of random fields
- Stochastic kriging for simulation metamodeling
- The design and analysis of computer experiments.
Cited in
(59)- The use of the Karhunen Loève expansion in the design of computer experiments
- A solution to the ill-conditioning of gradient-enhanced covariance matrices for Gaussian processes
- Flood hazard model calibration using multiresolution model output
- Active learning for efficiently training emulators of computationally expensive mathematical models
- Solving Bayesian inverse problems with expensive likelihoods using constrained Gaussian processes and active learning
- Screening the Discrepancy Function of a Computer Model
- A Global-Local Approximation Framework for Large-Scale Gaussian Process Modeling
- Sensitivity Prewarping for Local Surrogate Modeling
- Generalized Computer Model Calibration for Radiation Transport Simulation
- Sequential Optimization in Locally Important Dimensions
- \texttt{GLISp-r}: a preference-based optimization algorithm with convergence guarantees
- Modeling and Active Learning for Experiments with Quantitative-Sequence Factors
- The effect of the nugget on Gaussian process emulators of computer models
- Sparse radial basis function approximation with spatially variable shape parameters
- Efficient calibration for imperfect computer models
- High-fidelity hurricane surge forecasting using emulation and sequential experiments
- Sequential Bayesian polynomial chaos model selection for estimation of sensitivity indices
- Nonhierarchical multi-model fusion using spatial random processes
- Prediction of non-stationary response functions using a Bayesian composite Gaussian process
- Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
- A Bayesian mixed shrinkage prior procedure for spatial-stochastic basis selection and evaluation of gPC expansions: applications to elliptic SPDEs
- Emulation of multivariate simulators using thin-plate splines with application to atmospheric dispersion
- A discussion on adaptive designs for computer experiments
- Including a Nugget Effect in Lifted Brownian Covariance Models
- On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models
- Nested polynomial trends for the improvement of Gaussian process-based predictors
- Gradient and uncertainty enhanced sequential sampling for global fit
- Latent map Gaussian processes for mixed variable metamodeling
- Multi-output separable Gaussian process: towards an efficient, fully Bayesian paradigm for uncertainty quantification
- Comparison of Gaussian process modeling software
- Resolution Adaptive Fixed Rank Kriging
- Analysis methods for computer experiments: how to assess and what counts?
- Number of DoE Required for Estimating Different Quality Surrogate
- Leveraging the nugget parameter for efficient Gaussian process modeling
- Bayesian nonparametric policy search with application to periodontal recall intervals
- Diagnostics-driven nonstationary emulators using kernel mixtures
- Multi-output local Gaussian process regression: applications to uncertainty quantification
- Global fitting of the response surface via estimating multiple contours of a simulator
- Sequential Design with Mutual Information for Computer Experiments (MICE): Emulation of a Tsunami Model
- Efficient sequential experimental design for surrogate modeling of nested codes
- On the inference of applying Gaussian process modeling to a deterministic function
- Polar Gaussian processes and experimental designs in circular domains
- A multiobjective stochastic simulation optimization algorithm
- A non-intrusive solution to the ill-conditioning problem of the gradient-enhanced Gaussian covariance matrix for Gaussian processes
- Local Gaussian Process Model for Large-Scale Dynamic Computer Experiments
- Design of computer experiments: space filling and beyond
- Sequential design for computer experiments with a flexible Bayesian additive model
- Latin hypercube designs based on strong orthogonal arrays and kriging modelling to improve the payload distribution of trains
- A comparison of statistical emulation methodologies for multi‐wave calibration of environmental models
- A survey on kriging-based infill algorithms for multiobjective simulation optimization
- Composite Gaussian process models for emulating expensive functions
- On-site surrogates for large-scale calibration
- Calibration of computer models with multivariate output
- Gaussian processes with input location error and applications to the composite parts assembly process
- On the Bayesian treed multivariate Gaussian process with linear model of coregionalization
- Variable selection via a multi-stage strategy
- Coupling computer models through linking their statistical emulators
- A general framework for Vecchia approximations of Gaussian processes
- A Sequential Design Approach for Calibrating Dynamic Computer Simulators
This page was built for publication: Cases for the nugget in modeling computer experiments
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q693296)
