Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees

• URL: http://arxiv.org/abs/2603.19165v1
• Date: Thu, 19 Mar 2026 17:19:48 GMT
• Title: Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees
• Abstract summary: Physics-informed neural networks approximate solutions by minimizing residual losses at collocation points.<n>We prove that when neural approximations lie in a compact subset of the solution space, vanishing residual error guarantees convergence to the true solution.<n>We derive deterministic and probabilistic convergence results and provide certified generalization bounds translating residual, boundary, and initial errors into explicit solution error guarantees.
• Score: 6.335120646343732
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Uncertainty quantification for partial differential equations is traditionally grounded in discretization theory, where solution error is controlled via mesh/grid refinement. Physics-informed neural networks fundamentally depart from this paradigm: they approximate solutions by minimizing residual losses at collocation points, introducing new sources of error arising from optimization, sampling, representation, and overfitting. As a result, the generalization error in the solution space remains an open problem. Our main theoretical contribution establishes generalization bounds that connect residual control to solution-space error. We prove that when neural approximations lie in a compact subset of the solution space, vanishing residual error guarantees convergence to the true solution. We derive deterministic and probabilistic convergence results and provide certified generalization bounds translating residual, boundary, and initial errors into explicit solution error guarantees.

Related papers

• Approximation of solutions of parameter-dependent problems by residual neural networks [0.0]
  We develop a convergent scheme to train neural networks involving analytic activation functions based on gradient flows.<n>The main advantage of this approach is its simplicity of implementation.<n>We test the method by constructing residual neural network approximations of solutions of parametric problems.
  arXiv  Detail & Related papers  (2026-07-15T08:12:24Z)
• Generalized nonparametric regression in reproducing kernel Hilbert spaces: Consistency and rates of convergence [0.0]
  We develop a comprehensive theory for M-lev in reproducing spaces.<n>For Sobo spaces we obtain new rates that connect to spaces of smoothness with mixed smoothness functions.
  arXiv  Detail & Related papers  (2026-06-22T08:12:31Z)
• Verifiable Error Bounds for Physics-Informed Neural Network Solutions of Lyapunov and Hamilton-Jacobi-Bellman Equations [7.496694070699515]
  This paper develops verifiable error bounds for approximate solutions of Lyapunov and HJB equations.<n>For both the Lyapunov and HJB PDEs, we show that a verifiable residual bound yields relative error bounds with respect to the true solutions.<n>We show that one-sided residual bounds already imply that the approximation itself defines a valid Lyapunov or control Lyapunov function.
  arXiv  Detail & Related papers  (2026-03-20T00:58:51Z)
• Building Trust in PINNs: Error Estimation through Finite Difference Methods [52.92887996882041]
  Physics-informed neural networks (PINNs) constitute a flexible deep learning approach for solving partial differential equations (PDEs)<n>Despite their flexibility, PINNs offer limited insight into how their predictions deviate from the true solution, hindering trust in their prediction quality.<n>We propose a lightweight post-hoc method that addresses this gap by producing pointwise error estimates for PINN predictions.
  arXiv  Detail & Related papers  (2026-03-16T16:51:42Z)
• Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimation [3.8135482236014133]
  Minimizing PDE-residual losses is a common strategy to promote physical consistency in neural operators.<n>This work develops a variationally correct operator learning framework by constructing first-order system least-squares (FOSLS) objectives.<n>We provide a rigorous convergence analysis that bounds the total error by the sum of finite element discretization bias, reduced basis truncation error, neural network approximation error, and statistical estimation errors.
  arXiv  Detail & Related papers  (2025-12-24T18:37:59Z)
• The Hidden Cost of Approximation in Online Mirror Descent [56.99972253009168]
  Online mirror descent (OMD) is a fundamental algorithmic paradigm that underlies many algorithms in optimization, machine learning and sequential decision-making.<n>In this work we initiate a systematic study into inexact OMD, and uncover an intricate relation between regularizer smoothness and robustness to approximation errors.
  arXiv  Detail & Related papers  (2025-11-27T10:09:07Z)
• Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis [0.0]
  We present a unified theoretical framework for analyzing the stability and consistency of Physics-Informed Neural Networks (PINNs)<n>PINNs approximate solutions to partial differential equations (PDEs) by minimizing residual losses over sampled collocation and boundary points.<n>We formalize both operator-level and variational notions of consistency, proving that residual minimization in Sobolev norms leads to convergence in energy and uniform norms under mild regularity.
  arXiv  Detail & Related papers  (2025-06-16T14:41:15Z)
• Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum [56.37522020675243]
  We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. We show that due to their larger allowable stepsizes, our new normalized error feedback algorithms outperform their non-normalized counterparts on various tasks.
  arXiv  Detail & Related papers  (2024-10-22T10:19:27Z)
• Modify Training Directions in Function Space to Reduce Generalization Error [9.821059922409091]
  We propose a modified natural gradient descent method in the neural network function space based on the eigendecompositions of neural tangent kernel and Fisher information matrix. We explicitly derive the generalization error of the learned neural network function using theoretical methods from eigendecomposition and statistics theory.
  arXiv  Detail & Related papers  (2023-07-25T07:11:30Z)
• Robust Estimation for Nonparametric Families via Generative Adversarial Networks [92.64483100338724]
  We provide a framework for designing Generative Adversarial Networks (GANs) to solve high dimensional robust statistics problems. Our work extend these to robust mean estimation, second moment estimation, and robust linear regression. In terms of techniques, our proposed GAN losses can be viewed as a smoothed and generalized Kolmogorov-Smirnov distance.
  arXiv  Detail & Related papers  (2022-02-02T20:11:33Z)
• Error Estimation and Correction from within Neural Network Differential Equation Solvers [3.04585143845864]
  We describe a strategy for constructing error estimates and corrections for Neural Network Differential Equation solvers. Our methods do not require advance knowledge of the true solutions and obtain explicit relationships between loss functions and the error associated with solution estimates.
  arXiv  Detail & Related papers  (2020-07-09T11:01:44Z)
• Neural Control Variates [71.42768823631918]
  We show that a set of neural networks can face the challenge of finding a good approximation of the integrand. We derive a theoretically optimal, variance-minimizing loss function, and propose an alternative, composite loss for stable online training in practice. Specifically, we show that the learned light-field approximation is of sufficient quality for high-order bounces, allowing us to omit the error correction and thereby dramatically reduce the noise at the cost of negligible visible bias.
  arXiv  Detail & Related papers  (2020-06-02T11:17:55Z)
• Approximation Schemes for ReLU Regression [80.33702497406632]
  We consider the fundamental problem of ReLU regression. The goal is to output the best fitting ReLU with respect to square loss given to draws from some unknown distribution.
  arXiv  Detail & Related papers  (2020-05-26T16:26:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.