Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations

• URL: http://arxiv.org/abs/2405.01680v2
• Date: Thu, 13 Jun 2024 00:39:43 GMT
• Title: Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations
• Authors: Nima Hosseini Dashtbayaz, Ghazal Farhani, Boyu Wang, Charles X. Ling,
• Abstract summary: We show that under certain conditions, the residual loss of PINNs can be globally minimized by a wide neural network. An activation function with well-behaved high-order derivatives plays a crucial role in minimizing the residual loss. The established theory paves the way for designing and choosing effective activation functions for PINNs.
• Score: 5.731640425517324
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The residual loss in Physics-Informed Neural Networks (PINNs) alters the simple recursive relation of layers in a feed-forward neural network by applying a differential operator, resulting in a loss landscape that is inherently different from those of common supervised problems. Therefore, relying on the existing theory leads to unjustified design choices and suboptimal performance. In this work, we analyze the residual loss by studying its characteristics at critical points to find the conditions that result in effective training of PINNs. Specifically, we first show that under certain conditions, the residual loss of PINNs can be globally minimized by a wide neural network. Furthermore, our analysis also reveals that an activation function with well-behaved high-order derivatives plays a crucial role in minimizing the residual loss. In particular, to solve a $k$-th order PDE, the $k$-th derivative of the activation function should be bijective. The established theory paves the way for designing and choosing effective activation functions for PINNs and explains why periodic activations have shown promising performance in certain cases. Finally, we verify our findings by conducting a set of experiments on several PDEs. Our code is publicly available at https://github.com/nimahsn/pinns_tf2.

Related papers

• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• 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)
• Characteristics-Informed Neural Networks for Forward and Inverse Hyperbolic Problems [0.0]
  We propose characteristic-informed neural networks (CINN) for solving forward and inverse problems involving hyperbolic PDEs. CINN encodes the characteristics of the PDE in a general-purpose deep neural network trained with the usual MSE data-fitting regression loss. Preliminary results indicate that CINN is able to improve on the accuracy of the baseline PINN, while being nearly twice as fast to train and avoiding non-physical solutions.
  arXiv  Detail & Related papers  (2022-12-28T18:38:53Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Critical Investigation of Failure Modes in Physics-informed Neural Networks [0.9137554315375919]
  We show that a physics-informed neural network with a composite formulation produces highly non- learned loss surfaces that are difficult to optimize. We also assess the training both approaches on two elliptic problems with increasingly complex target solutions.
  arXiv  Detail & Related papers  (2022-06-20T18:43:35Z)
• Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next [5.956366179544257]
  Physic-Informed Neural Networks (PINN) are neural networks (NNs) that encode model equations. PINNs are nowadays used to solve PDEs, fractional equations, and integral-differential equations.
  arXiv  Detail & Related papers  (2022-01-14T19:05:44Z)
• Topological obstructions in neural networks learning [67.8848058842671]
  We study global properties of the loss gradient function flow. We use topological data analysis of the loss function and its Morse complex to relate local behavior along gradient trajectories with global properties of the loss surface.
  arXiv  Detail & Related papers  (2020-12-31T18:53:25Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)

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.