Similar papers
Preprint
Aug 2026
Multi-output Gaussian process prediction of physical fields under linear equality constraints
A robust framework for jointly modeling constrained multi-field data based on a linearly-constrained multi-output GP approach based on a specific kernel parametrization which is trained on the latent space of row-wise PCA.
Mahamat Hamdan Nassouradine, C. Gauchy, Pierre-Emmanuel Angeli et al.
· 0 citations
Preprint
Aug 2026
Control variates with neural surrogates for uncertainty quantification in kinetic equations
This work analyzes the case in which the reduced model is replaced by a neural surrogate rather than evaluated through a classical numerical scheme and shows that the resulting estimator remains unbiased and that the change in the optimal variance induced by the neural approximation is controlled by the error between t...
Wei Chen, G. Dimarco, L. Pareschi
· 0 citations
2026
Nonparametric Stochastic Subspaces via the Bootstrap Method for Characterizing Model Error
Reliable forward uncertainty quantification in engineering requires methods that account for aleatory and epistemic uncertainties. In many applications, epistemic effects arising from uncertain parameters and model form dominate prediction error and strongly influence engineering decisions. Because distinguishing and...
Akash Yadav, Ruda Zhang
· ASCE-ASME Journal of Risk an... · 0 citations
Open access
Aug 2026
Dimensionally consistent surrogate modelling through dimensional analysis and harmonic expansions
Dimensional homogeneity is a fundamental constraint on physically meaningful models, requiring invariance under changes of units. We present a data-driven method for constructing surrogate models that satisfy this constraint at the level of the hypothesis class. Starting from a dimension matrix of measured variable...
Ernest Tarrus, H. Gisbert
· Scientific Reports · 0 citations
A Systematic Analysis of Automatic Differentiation versus Discretization-based Constraints for Physics-Informed PDE Solvers
As nonlinearity strengthens, the accuracy advantage of discretization-based constraints becomes increasingly pronounced, with smaller optimization errors compensating for the truncation errors, and the more complex the nonlinearity and boundary conditions, the greater the advantage of GNN over MLP.
Xing Guo, Hong-Wei Tang, Ze-Wei Meng et al.
· 0 citations
Preprint
Aug 2026
Reliable and efficient steady CFD from surrogate predictions through Newton-Krylov correction
A solver-coupled surrogate-Newton framework that uses surrogate predictions as high-quality initial guesses for Newton-Krylov iterations, thereby combining rapid global flow-field prediction with high-accuracy numerical convergence at the terminal stage is developed.
Ming Lei, Weishao Tang, Yufei Zhang et al.
· 0 citations