Multiresolution functional ANOVA for large-scale, many-input computer experiments
From MaRDI portal
Abstract: The Gaussian process is a standard tool for building emulators for both deterministic and stochastic computer experiments. However, application of Gaussian process models is greatly limited in practice, particularly for large-scale and many-input computer experiments that have become typical. We propose a multi-resolution functional ANOVA model as a computationally feasible emulation alternative. More generally, this model can be used for large-scale and many-input non-linear regression problems. An overlapping group lasso approach is used for estimation, ensuring computational feasibility in a large-scale and many-input setting. New results on consistency and inference for the (potentially overlapping) group lasso in a high-dimensional setting are developed and applied to the proposed multi-resolution functional ANOVA model. Importantly, these results allow us to quantify the uncertainty in our predictions. Numerical examples demonstrate that the proposed model enjoys marked computational advantages. Data capabilities, both in terms of sample size and dimension, meet or exceed best available emulation tools while meeting or exceeding emulation accuracy.
Recommendations
- ANOVA Gaussian process modeling for high-dimensional stochastic computational models
- Scaled Vecchia approximation for fast computer-model emulation
- Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions
- Computer experiments: a review
- Computer emulation with nonstationary Gaussian processes
Cites work
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 47282 (Why is no real title available?)
- scientific article; zbMATH DE number 1034037 (Why is no real title available?)
- scientific article; zbMATH DE number 1077338 (Why is no real title available?)
- scientific article; zbMATH DE number 5056239 (Why is no real title available?)
- scientific article; zbMATH DE number 2231192 (Why is no real title available?)
- A general theory of hypothesis tests and confidence regions for sparse high dimensional models
- Accurate emulators for large-scale computer experiments
- Analyzing bagging
- Approximate efficiency of a selection procedure for the number of regression variables
- Asymptotic optimality for \(C_ p\), \(C_ L\), cross-validation and generalized cross-validation: Discrete index set
- Bagging predictors
- Component selection and smoothing in multivariate nonparametric regression
- Design and analysis of computer experiments. With comments and a rejoinder by the authors
- Efficient emulators of computer experiments using compactly supported correlation functions, with an application to cosmology
- Experiments. Planning, analysis and optimization.
- Exploiting Variance Reduction Potential in Local Gaussian Process Search
- Fast prediction of deterministic functions using sparse grid experimental designs
- Functional aggregation for nonparametric regression.
- Lasso-type recovery of sparse representations for high-dimensional data
- Massively parallel approximate Gaussian process regression
- Model Selection and Estimation in Regression with Grouped Variables
- Monte Carlo Variance of Scrambled Net Quadrature
- Multivariate adaptive regression splines
- On bagging and nonlinear estimation
- Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree
- Polynomial splines and their tensor products in extended linear modeling. (With discussions)
- Regularization parameter selections via generalized information criterion
- Scattered Data Approximation
- Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
- Smoothing spline ANOVA for exponential families, with application to the Wisconsin epidemiological study of diabetic retinopathy. (The 1994 Neyman Memorial Lecture)
- Sparse additive models
- Stochastic processes with sample paths in reproducing kernel Hilbert spaces
- Stochastic simulation: Algorithms and analysis
- Strictly Proper Scoring Rules, Prediction, and Estimation
- The Group Lasso for Logistic Regression
- The design and analysis of computer experiments.
- Theory of Reproducing Kernels
- Tuning parameter selectors for the smoothly clipped absolute deviation method
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(13)- Boosting on the functional ANOVA decomposition
- Scaled Vecchia approximation for fast computer-model emulation
- Sequential Learning of Active Subspaces
- A sequential split-and-conquer approach for the analysis of big dependent data in computer experiments
- Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions
- Predictive Subdata Selection for Computer Models
- ANOVA Gaussian process modeling for high-dimensional stochastic computational models
- A Clustered Gaussian Process Model for Computer Experiments
- Sensitivity analysis and emulation for functional data using Bayesian adaptive splines
- Linear screening for high-dimensional computer experiments
- On the inference of applying Gaussian process modeling to a deterministic function
- MRFA
- Projection pursuit emulation for many-input computer experiments
This page was built for publication: Multiresolution functional ANOVA for large-scale, many-input computer experiments
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q147162)
