Neuro-symbolic partial differential equation solver
Not on the map. Why?
Abstract (arXiv)
We present a highly scalable strategy for developing mesh-free neuro-symbolic partial differential equation solvers from existing numerical discretizations found in scientific computing. This strategy is unique in that it can be used to efficiently train neural network surrogate models for the solution functions and the differential operators, while retaining the accuracy and convergence properties of state-of-the-art numerical solvers. This neural bootstrapping method is based on minimizing residuals of discretized differential systems on a set of random collocation points with respect to the trainable parameters of the neural network, achieving unprecedented resolution and optimal scaling for solving physical and biological systems.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 25 Oct 2022.
Builds on
19 of 45 references.
References · 19
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
- 2018On the Spectral Bias of Neural Networkscited by 1,321
- 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 722
- 2017DGM: A deep learning algorithm for solving partial differential equationscited by 674
- 2021Characterizing possible failure modes in physics-informed neural networkscited by 632
- 2020When and why PINNs fail to train: A neural tangent kernel perspectivecited by 629
- 2017The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problemscited by 581
- 2021Machine learning accelerated computational fluid dynamicscited by 461
- 2020Model Reduction and Neural Networks for Parametric PDEscited by 257
- 2020Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solverscited by 201
- 2018Measuring the Effects of Data Parallelism on Neural Network Trainingcited by 190
7 more
- 2020Learning to Control PDEs with Differentiable Physicscited by 131
- 2022JAX-FLUIDS: A fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flowscited by 36
- 2020Solving inverse-PDE problems with physics-aware neural networkscited by 27
- 2019Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learningcited by 23
- 2019Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networkscited by 21
- 2017Neural network augmented inverse problems for PDEscited by 11
- 2021A non-parametric shape optimization approach for solving inverse problems in directed self-assembly of block copolymerscited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.