Investigating the Ability of PINNs To Solve Burgers' PDE Near Finite-Time BlowUp
Not on the map. Why?
Abstract (arXiv)
Physics Informed Neural Networks (PINNs) have been achieving ever newer feats of solving complicated PDEs numerically while offering an attractive trade-off between accuracy and speed of inference. A particularly challenging aspect of PDEs is that there exist simple PDEs which can evolve into singular solutions in finite time starting from smooth initial conditions. In recent times some striking experiments have suggested that PINNs might be good at even detecting such finite-time blow-ups. In this work, we embark on a program to investigate this stability of PINNs from a rigorous theoretical viewpoint. Firstly, we derive generalization bounds for PINNs for Burgers' PDE, in arbitrary dimensions, under conditions that allow for a finite-time blow-up. Then we demonstrate via experiments that our bounds are significantly correlated to the ℓ2-distance of the neurally found surrogate from the true blow-up solution, when computed on sequences of PDEs that are getting increasingly close to a blow-up.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 32 of its 80 references that are in the map. First posted on arXiv 8 Oct 2023.
Builds on
32 of 80 references.
References · 32
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2018On the Spectral Bias of Neural Networkscited by 1,341
- 2015Automatic differentiation in machine learning: a surveycited by 855
- 2017DGM: A deep learning algorithm for solving partial differential equationscited by 678
- 2021Characterizing possible failure modes in physics-informed neural networkscited by 643
- 2020When and why PINNs fail to train: A neural tangent kernel perspectivecited by 634
- 2017The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problemscited by 583
- 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 540
- 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 533
- 2017A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networkscited by 314
- 2018Stronger generalization bounds for deep nets via a compression approachcited by 307
- 2019Towards Physics-informed Deep Learning for Turbulent Flow Predictioncited by 204
20 more
- 2022Respecting causality is all you need for training physics-informed neural networkscited by 156
- 2018Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networkscited by 142
- 2020Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEscited by 116
- 2020Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learningcited by 77
- 2022Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Samplingcited by 73
- 2021Physics-informed neural networks for solving Reynolds-averaged Navierunicodex2013Stokes equationscited by 68
- 2019Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Predictioncited by 67
- 2017Data-driven discovery of Koopman eigenfunctions for controlcited by 64
- 2022Error estimates for physics informed neural networks approximating the Navier-Stokes equationscited by 63
- 2021Learning in Sinusoidal Spaces with Physics-Informed Neural Networkscited by 62
- 2021When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?cited by 58
- 2021Neural Stochastic PDEs: Resolution-Invariant Learning of Continuous Spatiotemporal Dynamicscited by 47
- 2021Learning Dissipative Dynamics in Chaotic Systemscited by 42
- 2020Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3Dcited by 27
- 2020Active Training of Physics-Informed Neural Networks to Aggregate and Interpolate Parametric Solutions to the Navier-Stokes Equationscited by 24
- 2022On the Role of Fixed Points of Dynamical Systems in Training Physics-Informed Neural Networkscited by 23
- 2022Is L2 Physics-Informed Loss Always Suitable for Training Physics-Informed Neural Network?cited by 23
- 2021Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equationscited by 13
- 2023Sparsity-aware generalization theory for deep neural networkscited by 8
- 2021A Study of the Mathematics of Deep Learningcited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.