Gradient-enhanced spline dimensional decomposition for uncertainty quantification with limited training samples

DOI10.48550/arXiv.2607.14615MaRDI QIDQ7284096arXivFDO

Authors Eunho Heo, Dongjin Lee

Publication date 16 July 2026

Published in arXiv

Tldr We propose a novel method for uncertainty quantification with limited training samples using spline dimensional decomposition (SDD), by incorporating gradient information and balancing function and derivative blocks through ridge regression in Sobolev coordinates. This results in improved accuracy over standard SDD and Kriging, especially for higher dimensions and larger uncertainties.

Full work available at URL https://doi.org/10.48550/arXiv.2607.14615

arXiv classification

math.NA

Cites work

• A Class of Statistics with Asymptotically Normal Distribution
• A polynomial dimensional decomposition for stochastic computing
• A Spline Dimensional Decomposition for Uncertainty Quantification in High Dimensions
• A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
• An introduction to the adjoint approach to design
• Bayesian Design and Analysis of Computer Experiments: Use of Derivatives in Surface Prediction
• Component-wise reduced order model lattice-type structure design
• Efficient input-output model representations
• High-Order Collocation Methods for Differential Equations with Random Inputs
• Multifidelity conditional value-at-risk estimation by dimensionally decomposed generalized polynomial chaos-Kriging
• Non-uniform rational basis spline hyper-surfaces for metamodelling
• Numerical integration using sparse grids
• On calculating with B-splines
• Regression Shrinkage and Selection Via the Lasso
• Reliability-based design optimization with confidence level under input model uncertainty due to limited test data
• Stochastic isogeometric analysis on arbitrary multipatch domains by spline dimensional decomposition
• The Numerical Evaluation of B-Splines
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Uncertainty quantification by optimal spline dimensional decomposition
• Variance-based adaptive sequential sampling for polynomial chaos expansion

This page was built for publication: Gradient-enhanced spline dimensional decomposition for uncertainty quantification with limited training samples

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7284096)