Compressive sensing with cross-validation and stop-sampling for sparse polynomial chaos expansions
From MaRDI portal
Abstract: Compressive sensing is a powerful technique for recovering sparse solutions of underdetermined linear systems, which is often encountered in uncertainty quantification analysis of expensive and high-dimensional physical models. We perform numerical investigations employing several compressive sensing solvers that target the unconstrained LASSO formulation, with a focus on linear systems that arise in the construction of polynomial chaos expansions. With core solvers of l1_ls, SpaRSA, CGIST, FPC_AS, and ADMM, we develop techniques to mitigate overfitting through an automated selection of regularization constant based on cross-validation, and a heuristic strategy to guide the stop-sampling decision. Practical recommendations on parameter settings for these techniques are provided and discussed. The overall method is applied to a series of numerical examples of increasing complexity, including large eddy simulations of supersonic turbulent jet-in-crossflow involving a 24-dimensional input. Through empirical phase-transition diagrams and convergence plots, we illustrate sparse recovery performance under structures induced by polynomial chaos, accuracy and computational tradeoffs between polynomial bases of different degrees, and practicability of conducting compressive sensing for a realistic, high-dimensional physical application. Across test cases studied in this paper, we find ADMM to have demonstrated empirical advantages through consistent lower errors and faster computational times.
Recommendations
- Divide and conquer: an incremental sparsity promoting compressive sampling approach for polynomial chaos expansions
- Data-driven compressive sensing and applications in uncertainty quantification
- Efficient uncertainty quantification of stochastic CFD problems using sparse polynomial chaos and compressed sensing
- Sparse polynomial chaos expansions via compressed sensing and D-optimal design
- Some greedy algorithms for sparse polynomial chaos expansions
Cites work
- A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization, and continuation
- A generalized sampling and preconditioning scheme for sparse approximation of polynomial chaos expansions
- A new look at the statistical model identification
- A weighted _1-minimization approach for sparse polynomial chaos expansions
- Adaptive greedy approximations
- Adaptive sparse polynomial chaos expansion based on least angle regression
- Atomic decomposition by basis pursuit
- Bayes Factors
- Bayesian Compressive Sensing
- Bayesian Compressive Sensing Using Laplace Priors
- Bayesian model selection and model averaging
- Compressed sensing
- Compressive sampling of polynomial chaos expansions: convergence analysis and sampling strategies
- Dimension-adaptive tensor-product quadrature
- Dimensionality reduction for complex models via Bayesian compressive sensing
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Enhancing \(\ell_1\)-minimization estimates of polynomial chaos expansions using basis selection
- Estimating the dimension of a model
- Fast numerical methods for stochastic computations: a review
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution
- High dimensional polynomial interpolation on sparse grids
- scientific article; zbMATH DE number 49187 (Why is no real title available?)
- Least angle regression. (With discussion)
- Numerical integration using sparse grids
- Observed universality of phase transitions in high-dimensional geometry, with implications for modern data analysis and signal processing
- On the convergence of generalized polynomial chaos expansions
- On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals
- Probing the Pareto frontier for basis pursuit solutions
- Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
- Sequential Design of Experiment for Sparse Polynomial Chaos Expansions
- Sparse Legendre expansions via _1-minimization
- Sparse Reconstruction by Separable Approximation
- Spectral Methods for Uncertainty Quantification
- The interaction of jets with crossflow
- The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
- Uncertainty Quantification and Polynomial Chaos Techniques in Computational Fluid Dynamics
Cited in
(20)- A generalized multi-fidelity simulation method using sparse polynomial chaos expansion
- An ensemble synthetic eddy method for accurate treatment of inhomogeneous turbulence
- Compressive sensing adaptation for polynomial chaos expansions
- A hybrid sequential sampling strategy for sparse polynomial chaos expansion based on compressive sampling and Bayesian experimental design
- Some applications of compressed sensing in computational mechanics: model order reduction, manifold learning, data-driven applications and nonlinear dimensionality reduction
- Divide and conquer: an incremental sparsity promoting compressive sampling approach for polynomial chaos expansions
- Data-driven compressive sensing and applications in uncertainty quantification
- Subsampled Gauss quadrature nodes for estimating polynomial chaos expansions
- Compressive sensing Petrov-Galerkin approximation of high-dimensional parametric operator equations
- Sparse Recovery via ℓq-Minimization for Polynomial Chaos Expansions
- Compressed sensing with sparse corruptions: fault-tolerant sparse collocation approximations
- Sliced-Inverse-Regression--Aided Rotated Compressive Sensing Method for Uncertainty Quantification
- Using automatic differentiation for compressive sensing in uncertainty quantification
- Compressed Sensing With Cross Validation
- Sparse polynomial chaos expansions: literature survey and benchmark
- A general framework of rotational sparse approximation in uncertainty quantification
- A new surrogate modeling method combining polynomial chaos expansion and Gaussian kernel in a sparse Bayesian learning framework
- Data-driven projection pursuit adaptation of polynomial chaos expansions for dependent high-dimensional parameters
- Enhancing sparsity of Hermite polynomial expansions by iterative rotations
- Sparse polynomial chaos expansions using variational relevance vector machines
This page was built for publication: Compressive sensing with cross-validation and stop-sampling for sparse polynomial chaos expansions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3176252)
