mlsanityData to 14 Oct 2026

Random Neural Network Expressivity for Non-Linear Partial Differential Equations

arXiv 2605.25057 ↗First posted 24 May 2026math.NA cs.LG cs.NAcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initialization for fully trainable deep learning methods. In this work, we study RaNN expressivity for learning solutions to non-linear partial differential equations (PDEs). Despite their widespread use in practical applications, a rigorous theoretical understanding of the approximation properties of RaNNs in this context remains limited. Here, we derive error bounds for RaNN approximations to time-dependent Sobolev functions and obtain a dimension-free approximation rate frac12 for sufficiently regular functions. We apply our results to two important classes of non-linear PDEs: Porous Medium Equations and Compressible Navier-Stokes Equations, showing that RaNNs are capable of efficiently approximating solutions to these complex, non-linear PDEs. Our theoretical analysis is supported by numerical experiments, showing that the obtained convergence rates extend beyond the considered setting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 72 references that are in the map. First posted on arXiv 24 May 2026.

Builds on

40 of 72 references.

References · 40

  1. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  2. 2018On the Spectral Bias of Neural Networkscited by 1,341
  3. 2017DGM: A deep learning algorithm for solving partial differential equationscited by 678
  4. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
  5. 2017The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problemscited by 583
  6. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
  7. 2019The generalization error of random features regression: Precise asymptotics and double descent curvecited by 413
  8. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 368
  9. 2014Breaking the Curse of Dimensionality with Convex Neural Networkscited by 331
  10. 2017Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equationscited by 191
  11. 2016Generalization Properties of Learning with Random Featurescited by 164
  12. 2022Respecting causality is all you need for training physics-informed neural networkscited by 156
28 more
  1. 2023An Expert's Guide to Training Physics-informed Neural Networkscited by 126
  2. 2020Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEscited by 116
  3. 2019A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Casecited by 114
  4. 2020Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating a class of inverse problems for PDEscited by 102
  5. 2020The Random Feature Model for Input-Output Maps between Banach Spacescited by 90
  6. 2023Tackling the Curse of Dimensionality with Physics-Informed Neural Networkscited by 79
  7. 2019Physics Informed Extreme Learning Machine (PIELM) -- A rapid method for the numerical solution of partial differential equationscited by 67
  8. 2020An overview on deep learning-based approximation methods for partial differential equationscited by 65
  9. 2015Neural Network with Unbounded Activation Functions is Universal Approximatorcited by 63
  10. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 54
  11. 2020Approximation Bounds for Random Neural Networks and Reservoir Systemscited by 52
  12. 2024Numerical analysis of physics-informed neural networks and related models in physics-informed machine learningcited by 39
  13. 2021Random feature neural networks learn Black-Scholes type PDEs without curse of dimensionalitycited by 34
  14. 2018Learning with SGD and Random Featurescited by 33
  15. 2021Neural networks-based algorithms for stochastic control and PDEs in financecited by 26
  16. 2023Error Bounds for Learning with Vector-Valued Random Featurescited by 23
  17. 2018Approximation and Estimation for High-Dimensional Deep Learning Networkscited by 22
  18. 2023An Extreme Learning Machine-Based Method for Computational PDEs in Higher Dimensionscited by 21
  19. 2023Sampling weights of deep neural networkscited by 20
  20. 2022Ridges, Neural Networks, and the Radon Transformcited by 18
  21. 2023Universal approximation property of Banach space-valued random feature models including random neural networkscited by 13
  22. 2024Full error analysis of the random deep splitting method for nonlinear parabolic PDEs and PIDEscited by 12
  23. 2024Random Representations Outperform Online Continually Learned Representationscited by 11
  24. 2023A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regressioncited by 8
  25. 2024Fast training of accurate physics-informed neural networks without gradient descentcited by 8
  26. 2024An Overview on Machine Learning Methods for Partial Differential Equations: from Physics Informed Neural Networks to Deep Operator Learningcited by 6
  27. 2025Random Feature Representation Boostingcited by 4
  28. 2024RandNet-Parareal: a time-parallel PDE solver using Random Neural Networkscited by 3

Built on by

Not cited yet.