mlsanityData to 7 Oct 2026

Neural network surrogates with uncertainty quantification for inverse problems in partial differential equations

arXiv 2606.20417 ↗First posted 18 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Inverse problems for differential equations arise throughout science and engineering, where one seeks to infer unknown model parameters from noisy or incomplete observations. Traditional numerical methods for these problems are often computationally expensive, particularly in Bayesian settings where evaluating the likelihood becomes costly for complex forward models and high-dimensional parameter spaces. To address this challenge, we introduce DeepGaLA, a neural-network surrogate for differential equation solvers that provides uncertainty-aware predictions, reducing overconfident inference when training data are limited. To evaluate the fidelity of the surrogate-induced posterior approximations in practice, we show that a short run of delayed-acceptance Markov chain Monte Carlo can serve as an effective diagnostic. Across a range of numerical experiments, DeepGaLA delivers forward-model approximations with accuracy comparable to established Gaussian-process surrogates, while better maintaining efficiency as parameter dimension grows. Moreover, it can incorporate differential-equation constraints, including in nonlinear settings. Overall, these results indicate that uncertainty-quantified neural surrogates can enable scalable and reliable Bayesian inference for inverse problems in complex systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 80 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

35 of 80 references.

References · 35

  1. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2018On the Spectral Bias of Neural Networkscited by 1,321
  7. 2017DGM: A deep learning algorithm for solving partial differential equationscited by 674
  8. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 603
  9. 2017The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problemscited by 581
  10. 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 537
  11. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 516
  12. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
23 more
  1. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  2. 2020On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networkscited by 279
  3. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
  4. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  5. 2017Machine Learning of Linear Differential Equations using Gaussian Processescited by 139
  6. 2021Solving and Learning Nonlinear PDEs with Gaussian Processescited by 128
  7. 2023An Expert's Guide to Training Physics-informed Neural Networkscited by 119
  8. 2020Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEscited by 115
  9. 2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 105
  10. 2021Sharp Bounds on the Approximation Rates, Metric Entropy, and n-widths of Shallow Neural Networkscited by 86
  11. 2021On the approximation of functions by tanh neural networkscited by 81
  12. 2020The Case for Bayesian Deep Learningcited by 68
  13. 2021The Modern Mathematics of Deep Learningcited by 63
  14. 2022Do Bayesian Neural Networks Need To Be Fully Stochastic?cited by 63
  15. 2015Probabilistic Numerics and Uncertainty in Computationscited by 59
  16. 2019Approximation spaces of deep neural networkscited by 51
  17. 2024Numerical analysis of physics-informed neural networks and related models in physics-informed machine learningcited by 39
  18. 2023Error Analysis of Kernel/GP Methods for Nonlinear and Parametric PDEscited by 21
  19. 2019On the well-posedness of Bayesian inverse problemscited by 20
  20. 2023Gaussian processes for Bayesian inverse problems associated with linear partial differential equationscited by 9
  21. 2023Introduction To Gaussian Process Regression In Bayesian Inverse Problems, With New ResultsOn Experimental Design For Weighted Error Measurescited by 6
  22. 2019A deep surrogate approach to efficient Bayesian inversion in PDE and integral equation modelscited by 5
  23. 2017Random forward models and log-likelihoods in Bayesian inverse problemscited by 4

Built on by

Not cited yet.