Data vs. Physics: The Apparent Pareto Front of Physics-Informed Neural Networks

• URL: http://arxiv.org/abs/2105.00862v2
• Date: Mon, 10 Jun 2024 12:18:28 GMT
• Title: Data vs. Physics: The Apparent Pareto Front of Physics-Informed Neural Networks
• Authors: Franz M. Rohrhofer, Stefan Posch, Clemens Gößnitzer, Bernhard C. Geiger,
• Abstract summary: Physics-informed neural networks (PINNs) have emerged as a promising deep learning method. PINNs are difficult to train and often require a careful tuning of loss weights when data and physics loss functions are combined.
• Score: 8.487185704099925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physics-informed neural networks (PINNs) have emerged as a promising deep learning method, capable of solving forward and inverse problems governed by differential equations. Despite their recent advance, it is widely acknowledged that PINNs are difficult to train and often require a careful tuning of loss weights when data and physics loss functions are combined by scalarization of a multi-objective (MO) problem. In this paper, we aim to understand how parameters of the physical system, such as characteristic length and time scales, the computational domain, and coefficients of differential equations affect MO optimization and the optimal choice of loss weights. Through a theoretical examination of where these system parameters appear in PINN training, we find that they effectively and individually scale the loss residuals, causing imbalances in MO optimization with certain choices of system parameters. The immediate effects of this are reflected in the apparent Pareto front, which we define as the set of loss values achievable with gradient-based training and visualize accordingly. We empirically verify that loss weights can be used successfully to compensate for the scaling of system parameters, and enable the selection of an optimal solution on the apparent Pareto front that aligns well with the physically valid solution. We further demonstrate that by altering the system parameterization, the apparent Pareto front can shift and exhibit locally convex parts, resulting in a wider range of loss weights for which gradient-based training becomes successful. This work explains the effects of system parameters on MO optimization in PINNs, and highlights the utility of proposed loss weighting schemes.

Related papers

• Network scaling and scale-driven loss balancing for intelligent poroelastography [2.665036498336221]
  A deep learning framework is developed for multiscale characterization of poroelastic media from full waveform data. Two major challenges impede direct application of existing state-of-the-art techniques for this purpose. We propose the idea of emphnetwork scaling where the neural property maps are constructed by unit shape functions composed into a scaling layer.
  arXiv  Detail & Related papers  (2024-10-27T23:06:29Z)
• Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems [49.11170948406405]
  State-of-the-art in automatic parameter estimation from video is addressed by training supervised deep networks on large datasets. We propose a method to estimate the physical parameters of any known, continuous governing equation from single videos.
  arXiv  Detail & Related papers  (2024-10-02T09:44:54Z)
• Physics-Informed Neural Network for Discovering Systems with Unmeasurable States with Application to Lithium-Ion Batteries [6.375364752891239]
  We introduce a robust method for training PINN that uses fewer loss terms and thus constructs a less complex landscape for optimization. Instead of having loss terms from each differential equation, this method embeds the dynamics into a loss function that quantifies the error between observed and predicted system outputs. This is accomplished by numerically integrating the predicted states from the neural network(NN) using known dynamics and transforming them to obtain a sequence of predicted outputs.
  arXiv  Detail & Related papers  (2023-11-27T23:35:40Z)
• 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)
• Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations [64.78260098263489]
  In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs) We show that PINNs eventually fail to produce correct solutions to these benchmarks as their complexity increases. We identify several reasons why this may be the case, including insufficient network capacity, poor conditioning of the ODEs, and high local curvature, as measured by the Laplacian of the PINN loss.
  arXiv  Detail & Related papers  (2022-10-14T15:01:32Z)
• 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)
• Understanding the Difficulty of Training Physics-Informed Neural Networks on Dynamical Systems [5.878411350387833]
  Physics-informed neural networks (PINNs) seamlessly integrate data and physical constraints into the solving of problems governed by differential equations. We study the physics loss function in the vicinity of fixed points of dynamical systems. We find that reducing the computational domain lowers the optimization complexity and chance of getting trapped with nonphysical solutions.
  arXiv  Detail & Related papers  (2022-03-25T13:50:14Z)
• 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)
• Physics-Informed Neural Operator for Learning Partial Differential Equations [55.406540167010014]
  PINO is the first hybrid approach incorporating data and PDE constraints at different resolutions to learn the operator. The resulting PINO model can accurately approximate the ground-truth solution operator for many popular PDE families.
  arXiv  Detail & Related papers  (2021-11-06T03:41:34Z)
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning [0.0]
  We observe the role of correctly weighting the combination of multiple competitive loss functions for training PINNs effectively. We propose a novel self-adaptive loss balancing of PINNs called ReLoBRaLo. Our simulation studies show that ReLoBRaLo training is much faster and achieves higher accuracy than training PINNs with other balancing methods.
  arXiv  Detail & Related papers  (2021-10-19T09:00:12Z)
• 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.