Mercer Kernels and Integrated Variance Experimental Design: Connections Between Gaussian Process Regression and Polynomial Approximation

DOI10.1137/15M1017119zbMath1342.62061arXiv1503.00021OpenAlexW2964029376MaRDI QIDQ5741201

Youssef M. Marzouk, Alex Gorodetsky

Publication date: 22 July 2016

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1503.00021

zbMATH Keywords

polynomial approximationapproximation theorycomputer experimentsuncertainty quantificationexperimental designGaussian process regressionkernel interpolation

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Algorithms for approximation of functions (65D15)

Related Items

Clustered active-subspace based local Gaussian process emulator for high-dimensional and complex computer models ⋮ Bayesian Quadrature, Energy Minimization, and Space-Filling Design ⋮ Adaptive Gaussian Process Approximation for Bayesian Inference with Expensive Likelihood Functions ⋮ Cholesky-Based Experimental Design for Gaussian Process and Kernel-Based Emulation and Calibration ⋮ Locally induced Gaussian processes for large-scale simulation experiments ⋮ Gradient-based optimization for regression in the functional tensor-train format ⋮ Optimal Off-line Experimentation for Games ⋮ An Adaptive Minimum Spanning Tree Multielement Method for Uncertainty Quantification of Smooth and Discontinuous Responses

Uses Software

• SciPy
• NLopt
• TESTPACK
• GitHub

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal designs for Gaussian process models via spectral decomposition
• Characterization of discontinuities in high-dimensional stochastic problems on adaptive sparse grids
• Sparse pseudospectral approximation method
• Stability of kernel-based interpolation
• Asymptotic analysis of stochastic programs
• The design and analysis of computer experiments.
• Dimension-adaptive tensor-product quadrature
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• Near-optimal data-independent point locations for radial basis function interpolation
• Positive integral operators in unbounded domains
• An extension of Mercer's theory to \(L^p\)
• High dimensional polynomial interpolation on sparse grids
• Batch sequential designs for computer experiments
• Spatial sampling design and covariance-robust minimax prediction based on convex design ideas
• Uncertainty Quantification given Discontinuous Model Response and a Limited Number of Model Runs
• Spectral Approximation of the IMSE Criterion for Optimal Designs in Kernel-Based Interpolation Models
• An Algorithm for the Construction of "D-Optimal" Experimental Designs
• Real Analysis and Probability
• An Exact Algorithm for Maximum Entropy Sampling
• Efficient Localization of Discontinuities in Complex Computational Simulations
• Mercer’s Theorem, Feature Maps, and Smoothing
• Adaptive Smolyak Pseudospectral Approximations
• Convergence of Unsymmetric Kernel‐Based Meshless Collocation Methods
• Sequential Design with Mutual Information for Computer Experiments (MICE): Emulation of a Tsunami Model
• On cardinal interpolation by Gaussian radial-basis functions: Properties of fundamental functions and estimates for Lebesgue constants