NeuralPCG: Learning Preconditioner for Solving Partial Differential Equations with Graph Neural Network

Yichen Li, Tao Du, Peter Yichen Chen, Wojciech Matusik

Keywords: Physics Simulation, Graph Neural Network, Applied Mathematics

Abstract: Fast and accurate partial differential equation (PDE) solvers empower scientific and engineering research. Classic numerical solvers provide unparalleled accuracy but often require extensive computation time. Machine learning solvers are significantly faster but lack convergence and accuracy guarantees. We present Neural-Network-Preconditioned Conjugate Gradient, or NeuralPCG, a novel linear second-order PDE solver that combines the benefits of classic iterative solvers and machine learning approaches. Our key observation is that both neural-network PDE solvers and classic preconditioners excel at obtaining fast but inexact solutions. NeuralPCG proposes to use neural network models to \emph{precondition} PDE systems in classic iterative solvers. Compared with neural-network PDE solvers, NeuralPCG achieves converging and accurate solutions (e.g.,1e-12 precision) by construction. Compared with classic solvers, NeuralPCG is faster via data-driven preconditioners. We demonstrate the efficacy and generalizability of NeuralPCG by conducting extensive experiments on various 2D and 3D linear second-order PDEs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )