Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations

• URL: http://arxiv.org/abs/2405.14099v3
• Date: Mon, 2 Sep 2024 21:40:41 GMT
• Title: Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
• Authors: Chuqi Chen, Yahong Yang, Yang Xiang, Wenrui Hao,
• Abstract summary: Neural network-based approaches have recently shown significant promise in solving partial differential equations (PDEs) in science and engineering. One advantage of the neural network methods for PDEs lies in its automatic differentiation (AD) In this paper, we quantitatively demonstrate the advantage of AD in training neural networks.
• Score: 7.890817997914349
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural network-based approaches have recently shown significant promise in solving partial differential equations (PDEs) in science and engineering, especially in scenarios featuring complex domains or incorporation of empirical data. One advantage of the neural network methods for PDEs lies in its automatic differentiation (AD), which necessitates only the sample points themselves, unlike traditional finite difference (FD) approximations that require nearby local points to compute derivatives. In this paper, we quantitatively demonstrate the advantage of AD in training neural networks. The concept of truncated entropy is introduced to characterize the training property. Specifically, through comprehensive experimental and theoretical analyses conducted on random feature models and two-layer neural networks, we discover that the defined truncated entropy serves as a reliable metric for quantifying the residual loss of random feature models and the training speed of neural networks for both AD and FD methods. Our experimental and theoretical analyses demonstrate that, from a training perspective, AD outperforms FD in solving PDEs.

Related papers

• A hybrid FEM-PINN method for time-dependent partial differential equations [9.631238071993282]
  We present a hybrid numerical method for solving evolution differential equations (PDEs) by merging the time finite element method with deep neural networks. The advantages of such a hybrid formulation are twofold: statistical errors are avoided for the integral in the time direction, and the neural network's output can be regarded as a set of reduced spatial basis functions.
  arXiv  Detail & Related papers  (2024-09-04T15:28:25Z)
• Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems [49.2319247825857]
  We show that diffusion-based generative models exhibit many properties favourable for neural operators. We propose to train a single model adaptable to multiple tasks, by alternating between the tasks during training.
  arXiv  Detail & Related papers  (2024-05-11T21:23:55Z)
• Neural Partial Differential Equations with Functional Convolution [30.35306295442881]
  We present a lightweighted neural PDE representation to discover the hidden structure and predict the solution of different nonlinear PDEs. We leverage the prior of translational similarity'' of numerical PDE differential operators to drastically reduce the scale of learning model and training data.
  arXiv  Detail & Related papers  (2023-03-10T04:25:38Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Learning Physics-Informed Neural Networks without Stacked Back-propagation [82.26566759276105]
  We develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks. In particular, we parameterize the PDE solution by the Gaussian smoothed model and show that, derived from Stein's Identity, the second-order derivatives can be efficiently calculated without back-propagation. Experimental results show that our proposed method can achieve competitive error compared to standard PINN training but is two orders of magnitude faster.
  arXiv  Detail & Related papers  (2022-02-18T18:07:54Z)
• Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations [9.823102211212582]
  We introduce the novel approach of employing multi-task learning techniques, the uncertainty-weighting loss and the gradients surgery, in the context of learning PDE solutions. In the experiments, our proposed methods are found to be effective and reduce the error on the unseen data points as compared to the previous approaches.
  arXiv  Detail & Related papers  (2021-04-29T13:17:46Z)
• Efficient training of physics-informed neural networks via importance sampling [2.9005223064604078]
  Physics-In Neural Networks (PINNs) are a class of deep neural networks that are trained to compute systems governed by partial differential equations (PDEs) We show that an importance sampling approach will improve the convergence behavior of PINNs training.
  arXiv  Detail & Related papers  (2021-04-26T02:45:10Z)
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method [0.0]
  We present a methodology combining neural networks with physical principle constraints in the form of partial differential equations (PDEs) The approach allows to train neural networks while respecting the PDEs as a strong constraint in the optimisation as apposed to making them part of the loss function. We demonstrate the method on a complex cardiac cell model problem using deep neural networks.
  arXiv  Detail & Related papers  (2021-01-04T13:36:06Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)
• Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction [79.81193813215872]
  We develop a hybrid (graph) neural network that combines a traditional graph convolutional network with an embedded differentiable fluid dynamics simulator inside the network itself. We show that we can both generalize well to new situations and benefit from the substantial speedup of neural network CFD predictions.
  arXiv  Detail & Related papers  (2020-07-08T21:23:19Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.