A fully Bayesian sparse polynomial chaos expansion approach with joint priors on the coefficients and global selection of terms

DOI10.1016/J.JCP.2023.112210arXiv2204.06043OpenAlexW4376604884MaRDI QIDQ6162876FDOQ6162876

Authors: Paul-Christian Bürkner, Ilja Kröker, Sergey Oladyshkin, Wolfgang Nowak 

Publication date: 16 June 2023

Published in: Journal of Computational Physics (Search for Journal in Brave)

Abstract: Polynomial chaos expansion (PCE) is a versatile tool widely used in uncertainty quantification and machine learning, but its successful application depends strongly on the accuracy and reliability of the resulting PCE-based response surface. High accuracy typically requires high polynomial degrees, demanding many training points especially in high-dimensional problems through the curse of dimensionality. So-called sparse PCE concepts work with a much smaller selection of basis polynomials compared to conventional PCE approaches and can overcome the curse of dimensionality very efficiently, but have to pay specific attention to their strategies of choosing training points. Furthermore, the approximation error resembles an uncertainty that most existing PCE-based methods do not estimate. In this study, we develop and evaluate a fully Bayesian approach to establish the PCE representation via joint shrinkage priors and Markov chain Monte Carlo. The suggested Bayesian PCE model directly aims to solve the two challenges named above: achieving a sparse PCE representation and estimating uncertainty of the PCE itself. The embedded Bayesian regularizing via the joint shrinkage prior allows using higher polynomial degrees for given training points due to its ability to handle underdetermined situations, where the number of considered PCE coefficients could be much larger than the number of available training points. We also explore multiple variable selection methods to construct sparse PCE expansions based on the established Bayesian representations, while globally selecting the most meaningful orthonormal polynomials given the available training data. We demonstrate the advantages of our Bayesian PCE and the corresponding sparsity-inducing methods on several benchmarks.

Full work available at URL: https://arxiv.org/abs/2204.06043

Recommendations

• Bayesian sparse polynomial chaos expansion for global sensitivity analysis
• Selection of polynomial chaos bases via Bayesian model uncertainty methods with applications to sparse approximation of PDEs with stochastic inputs
• An efficient and robust adaptive sampling method for polynomial chaos expansion in sparse Bayesian learning framework
• Optimal sparse polynomial chaos expansion for arbitrary probability distribution and its application on global sensitivity analysis
• A hybrid sequential sampling strategy for sparse polynomial chaos expansion based on compressive sampling and Bayesian experimental design
• On the use of sparse Bayesian learning-based polynomial chaos expansion for global reliability sensitivity analysis
• An efficient adaptive forward-backward selection method for sparse polynomial chaos expansion
• Multi-level multi-fidelity sparse polynomial chaos expansion based on Gaussian process regression
• Sparse polynomial chaos expansions using variational relevance vector machines
• Sparse polynomial chaos expansions: literature survey and benchmark

zbMATH Keywords

variable selectionBayesian inferenceshrinkage priorsuncertainty quantificationpolynomial chaos expansionsurrogate modeling

Mathematics Subject Classification ID

Linear inference, regression (62Jxx) Stochastic analysis (60Hxx) Probabilistic methods, stochastic differential equations (65Cxx)

Cites Work

• Title not available (Why is that?)
• An introduction to statistical learning. With applications in R
• Shrinkage priors for Bayesian penalized regression
• The no-U-turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo
• Rank-normalization, folding, and localization: an improved \(\widehat{R}\) for assessing convergence of MCMC (with Discussion)
• Title not available (Why is that?)
• Title not available (Why is that?)
• 10.1162/15324430152748236
• Sparsity information and regularization in the horseshoe and other shrinkage priors
• Practical Hilbert space approximate Bayesian Gaussian processes for probabilistic programming
• On the distribution of points in a cube and the approximate evaluation of integrals
• Title not available (Why is that?)
• Title not available (Why is that?)
• Some basic hypergeometric orthogonal polynomials that generalize Jacobi polynomials
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Title not available (Why is that?)
• On sensitivity estimation for nonlinear mathematical models
• On the convergence of generalized polynomial chaos expansions
• Title not available (Why is that?)
• Near-optimal data-independent point locations for radial basis function interpolation
• Modeling uncertainty in flow simulations via generalized polynomial chaos.
• Title not available (Why is that?)
• Default Bayesian analysis with global-local shrinkage priors
• Galerkin methods for linear and nonlinear elliptic stochastic partial differential equations
• The orthogonal development of non-linear functionals in series of Fourier-Hermite functionals
• Sparse Quadrature as an Alternative to Monte Carlo for Stochastic Finite Element Techniques
• Sparse polynomial chaos expansions and adaptive stochastic finite elements using a regression approach
• Adaptive Smolyak Pseudospectral Approximations
• Uncertainty quantification for systems of conservation laws
• Central-upwind schemes on triangular grids for hyperbolic systems of conservation laws
• Title not available (Why is that?)
• On the determinants of moment matrices
• The predictive Lasso
• Least squares polynomial chaos expansion: a review of sampling strategies
• Introduction to uncertainty quantification
• SAMBA: sparse approximation of moment-based arbitrary polynomial chaos
• Intrusive uncertainty quantification for hyperbolic-elliptic systems governing two-phase flow in heterogeneous porous media
• Regression-based sparse polynomial chaos for uncertainty quantification of subsurface flow models
• Bayesian updating via bootstrap filtering combined with data-driven polynomial chaos expansions: methodology and application to history matching for carbon dioxide storage in geological formations
• Bayesian sparse polynomial chaos expansion for global sensitivity analysis
• Surrogate-based Bayesian comparison of computationally expensive models: application to microbially induced calcite precipitation
• Comparison of data-driven uncertainty quantification methods for a carbon dioxide storage benchmark scenario
• Projective inference in high-dimensional problems: prediction and feature selection
• Bayesian Regression Using a Prior on the Model Fit: The R2-D2 Shrinkage Prior

Cited In (6)

• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
• Gaussian active learning on multi-resolution arbitrary polynomial chaos emulator: concept for bias correction, assessment of surrogate reliability and its application to the carbon dioxide benchmark
• The deep arbitrary polynomial chaos neural network or how deep artificial neural networks could benefit from data-driven homogeneous chaos theory
• An active sparse polynomial chaos expansion approach based on sequential relevance vector machine
• A new modified WINDMI jerk system with exponential and sinusoidal nonlinearities, its bifurcation analysis, multistability, circuit simulation and synchronization design
• A Bayesian mixed shrinkage prior procedure for spatial-stochastic basis selection and evaluation of gPC expansions: applications to elliptic SPDEs

This page was built for publication: A fully Bayesian sparse polynomial chaos expansion approach with joint priors on the coefficients and global selection of terms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6162876)