LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data

TL;DR

LordNet is a novel neural network architecture designed to efficiently learn solutions to parametric PDEs from physics-constrained loss, significantly reducing computational cost while improving accuracy and generalization over existing methods.

Contribution

The paper introduces LordNet, a neural network that models long-range entanglements in PDEs using matrix multiplications, enabling faster and more accurate solutions without simulated data.

Findings

LordNet achieves up to 40x speedup over traditional PDE solvers.

It outperforms other neural networks in accuracy and efficiency.

LordNet requires fewer parameters while maintaining high performance.

Abstract

Neural operators, as a powerful approximation to the non-linear operators between infinite-dimensional function spaces, have proved to be promising in accelerating the solution of partial differential equations (PDE). However, it requires a large amount of simulated data, which can be costly to collect. This can be avoided by learning physics from the physics-constrained loss, which we refer to it as mean squared residual (MSR) loss constructed by the discretized PDE. We investigate the physical information in the MSR loss, which we called long-range entanglements, and identify the challenge that the neural network requires the capacity to model the long-range entanglements in the spatial domain of the PDE, whose patterns vary in different PDEs. To tackle the challenge, we propose LordNet, a tunable and efficient neural network for modeling various entanglements. Inspired by the traditional solvers, LordNet models the long-range entanglements with a series of matrix multiplications, which can be seen as the low-rank approximation to the general fully-connected layers and extracts the dominant pattern with reduced computational cost. The experiments on solving Poisson's equation and (2D and 3D) Navier-Stokes equation demonstrate that the long-range entanglements from the MSR loss can be well modeled by the LordNet, yielding better accuracy and generalization ability than other neural networks. The results show that the Lordnet can be $40\times$ faster than traditional PDE solvers. In addition, LordNet outperforms other modern neural network architectures in accuracy and efficiency with the smallest parameter size.