Accurate emulators for large-scale computer experiments
From MaRDI portal
Publication:449978
DOI10.1214/11-AOS929zbMATH Open1246.65172arXiv1203.2433OpenAlexW2044571476MaRDI QIDQ449978FDOQ449978
Authors: Ben Haaland, Peter Z. G. Qian 
Publication date: 3 September 2012
Published in: The Annals of Statistics (Search for Journal in Brave)
Abstract: Large-scale computer experiments are becoming increasingly important in science. A multi-step procedure is introduced to statisticians for modeling such experiments, which builds an accurate interpolator in multiple steps. In practice, the procedure shows substantial improvements in overall accuracy, but its theoretical properties are not well established. We introduce the terms nominal and numeric error and decompose the overall error of an interpolator into nominal and numeric portions. Bounds on the numeric and nominal error are developed to show theoretically that substantial gains in overall accuracy can be attained with the multi-step approach.
Full work available at URL: https://arxiv.org/abs/1203.2433
Recommendations
interpolationreproducing kernel Hilbert spaceGaussian processcomputer experimentemulationradial basis functionlarge-scale problemmulti-step procedurenumerical technique
Roundoff error (65G50) Inequalities in approximation (Bernstein, Jackson, Nikol'ski?-type inequalities) (41A17) Stability and convergence of numerical methods for initial value and initial-boundary value problems involving PDEs (65M12)
Cites Work
- The design and analysis of computer experiments.
- Design and analysis of computer experiments. With comments and a rejoinder by the authors
- Compactly supported correlation functions
- Approximating Likelihoods for Large Spatial Data Sets
- Covariance tapering for likelihood-based estimation in large spatial data sets
- Theory of Reproducing Kernels
- A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
- Title not available (Why is that?)
- Title not available (Why is that?)
- Large Sample Properties of Simulations Using Latin Hypercube Sampling
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Monte Carlo Variance of Scrambled Net Quadrature
- Title not available (Why is that?)
- Scattered Data Approximation
- Orthogonal Array-Based Latin Hypercubes
- Title not available (Why is that?)
- Orthogonal arrays. Theory and applications
- Meshfree approximation methods with Matlab. With CD-ROM.
- Title not available (Why is that?)
- Multistep scattered data interpolation using compactly supported radial basis functions
- An algorithm for selecting a good value for the parameter \(c\) in radial basis function interpolation
- Monte Carlo estimates of the log determinant of large sparse matrices
- Title not available (Why is that?)
- On Latin hypercube sampling
- Title not available (Why is that?)
- Uniform Design: Theory and Application
- Construction of nested space-filling designs
- Nested space-filling designs for computer experiments with two levels of accuracy.
- Orthogonal and nearly orthogonal designs for computer experiments
- Construction of orthogonal and nearly orthogonal Latin hypercubes
- Sliced space-filling designs
- Orthogonal Column Latin Hypercubes and Their Application in Computer Experiments
- A construction method for orthogonal Latin hypercube designs
- A new and flexible method for constructing designs for computer experiments
- Scrambled net variance for integrals of smooth functions
- Multiscale analysis in Sobolev spaces on the sphere
- Orthogonal-maximin Latin hypercube designs
- Nested Latin hypercube designs
- Title not available (Why is that?)
- Multistep approximation algorithms: Improved convergence rates through postconditioning with smoothing kernels
- Multiscale analysis in Sobolev spaces on bounded domains
- Lattice sampling revisited: Monte Carlo variance of means over randomized orthogonal arrays
- On the asymptotic distribution of scrambled net quadrature.
- Error estimates for multilevel approximation using polyharmonic splines
- A combinatorial central limit theorem for randomized orthogonal array sampling designs
- Multilevel interpolation and approximation
- An approach to constructing nested space-filling designs for multi-fidelity computer experiments
- A theorem for selecting oa-based latin hypercubes using a distance criterion
- Nested lattice sampling: a new sampling scheme derived by randomizing nested orthogonal arrays
- A multivariate central limit theorem for randomized orthogonal array sampling designs in computer experiments
Cited In (25)
- Construction of high-dimensional high-separation distance designs
- Calibrating a large computer experiment simulating radiative shock hydrodynamics
- A theoretical framework for calibration in computer models: parametrization, estimation and convergence properties
- Known Boundary Emulation of Complex Computer Models
- Monotone Emulation of Computer Experiments
- Maximum Likelihood Estimation for a Smooth Gaussian Random Field Model
- Fast prediction of deterministic functions using sparse grid experimental designs
- Multiresolution functional ANOVA for large-scale, many-input computer experiments
- Composite Gaussian process models for emulating expensive functions
- Cross-validation-based adaptive sampling for Gaussian process models
- Transformation and Additivity in Gaussian Processes
- A Clustered Gaussian Process Model for Computer Experiments
- Predicting the Output From a Stochastic Computer Model When a Deterministic Approximation is Available
- A framework for controlling sources of inaccuracy in Gaussian process emulation of deterministic computer experiments
- Controlling Sources of Inaccuracy in Stochastic Kriging
- Functional-input Gaussian processes with applications to inverse scattering problems
- On the instability issue of gradient-enhanced Gaussian process emulators for computer experiments
- On the construction of nested space-filling designs
- Sequential Model-Based Optimization for Continuous Inputs with Finite Decision Space
- Predictive Subdata Selection for Computer Models
- Practical Heteroscedastic Gaussian Process Modeling for Large Simulation Experiments
- On the interface between nested designs and the multi-step interpolator
- A new and flexible design construction for orthogonal arrays for modern applications
- Variable selection and sensitivity analysis using dynamic trees, with an application to computer code performance tuning
- Stacking Designs: Designing Multifidelity Computer Experiments with Target Predictive Accuracy
Uses Software
This page was built for publication: Accurate emulators for large-scale computer experiments
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q449978)
