Learn Sharp Interface Solution by Homotopy Dynamics

• URL: http://arxiv.org/abs/2502.00488v2
• Date: Sun, 09 Feb 2025 01:54:47 GMT
• Title: Learn Sharp Interface Solution by Homotopy Dynamics
• Authors: Chuqi Chen, Yahong Yang, Yang Xiang, Wenrui Hao,
• Abstract summary: Training neural networks for solving partial differential equations (PDEs) is challenging due to certain parameters in the PDEs that introduce near-singularities in the loss function.<n>We introduce a novel method based on homotopy dynamics to effectively manipulate these parameters.<n> Experimentally, we demonstrate that our approach significantly accelerates convergence and improves the accuracy of sharp interface capturing.
• Score: 7.890817997914349
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Solving partial differential equations (PDEs) using neural networks has become a central focus in scientific machine learning. Training neural networks for sharp interface problems is particularly challenging due to certain parameters in the PDEs that introduce near-singularities in the loss function. In this study, we overcome this challenge by introducing a novel method based on homotopy dynamics to effectively manipulate these parameters. From a theoretical perspective, we analyze the effects of these parameters on training difficulty in sharp interface problems and establish the convergence of the proposed homotopy dynamics method. Experimentally, we demonstrate that our approach significantly accelerates convergence and improves the accuracy of sharp interface capturing. These findings present an efficient optimization strategy leveraging homotopy dynamics, offering a robust framework to extend the applicability of neural networks for solving PDEs with sharp

Related papers

• Which Optimizer Works Best for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks? [1.8175282137722093]
  Physics-In Arnold Neural Networks (PINNs) have revolutionized the computation of partial differential equations (PDEs)<n>These PINNs integrate PDEs into the neural network's training process as soft constraints.
  arXiv  Detail & Related papers  (2025-01-22T21:19:42Z)
• An Adaptive Collocation Point Strategy For Physics Informed Neural Networks via the QR Discrete Empirical Interpolation Method [1.2289361708127877]
  We propose an adaptive collocation point selection strategy utilizing the QR Discrete Empirical Interpolation Method (QR-DEIM) Our results on benchmark PDEs, including the wave, Allen-Cahn, and Burgers' equations, demonstrate that our QR-DEIM-based approach improves PINN accuracy compared to existing methods.
  arXiv  Detail & Related papers  (2025-01-13T21:24:15Z)
• Advancing Generalization in PINNs through Latent-Space Representations [71.86401914779019]
  Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs) We propose PIDO, a novel physics-informed neural PDE solver designed to generalize effectively across diverse PDE configurations. We validate PIDO on a range of benchmarks, including 1D combined equations and 2D Navier-Stokes equations.
  arXiv  Detail & Related papers  (2024-11-28T13:16:20Z)
• DiffGrad for Physics-Informed Neural Networks [0.0]
  Burgers' equation, a fundamental equation in fluid dynamics that is extensively used in PINNs, provides flexible results with the Adamprop. This paper introduces a novel strategy for solving Burgers' equation by incorporating DiffGrad with PINNs.
  arXiv  Detail & Related papers  (2024-09-05T04:39:35Z)
• Adversarial Learning for Neural PDE Solvers with Sparse Data [4.226449585713182]
  This study introduces a universal learning strategy for neural network PDEs, named Systematic Model Augmentation for Robust Training. By focusing on challenging and improving the model's weaknesses, SMART reduces generalization error during training under data-scarce conditions.
  arXiv  Detail & Related papers  (2024-09-04T04:18:25Z)
• Adapting Physics-Informed Neural Networks for Bifurcation Detection in Ecological Migration Models [0.16442870218029523]
  In this study, we explore the application of Physics-Informed Neural Networks (PINNs) to the analysis of bifurcation phenomena in ecological migration models. By integrating the fundamental principles of diffusion-advection-reaction equations with deep learning techniques, we address the complexities of species migration dynamics.
  arXiv  Detail & Related papers  (2024-09-01T08:00:31Z)
• VS-PINN: A fast and efficient training of physics-informed neural networks using variable-scaling methods for solving PDEs with stiff behavior [0.0]
  We propose a new method for training PINNs using variable-scaling techniques. We will demonstrate the effectiveness of the proposed method for these problems and confirm that it can significantly improve the training efficiency and performance of PINNs.
  arXiv  Detail & Related papers  (2024-06-10T14:11:15Z)
• Challenges in Training PINNs: A Loss Landscape Perspective [16.89714536706181]
  This paper explores challenges in training Physics-Informed Neural Networks (PINNs) We examine difficulties in minimizing the PINN loss function, particularly due to ill-conditioning caused by differential operators in the residual term. We introduce a novel second-order gradient, NysNewton-CG (NNCG), which significantly improves PINN performance.
  arXiv  Detail & Related papers  (2024-02-02T19:46:43Z)
• Deep Learning-based Analysis of Basins of Attraction [49.812879456944984]
  This research addresses the challenge of characterizing the complexity and unpredictability of basins within various dynamical systems. The main focus is on demonstrating the efficiency of convolutional neural networks (CNNs) in this field.
  arXiv  Detail & Related papers  (2023-09-27T15:41:12Z)
• A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks [52.5899851000193]
  We develop an ODE based IVP solver which prevents the network from getting ill-conditioned and runs in time linear in the number of parameters. We show that current methods based on this approach suffer from two key issues. First, following the ODE produces an uncontrolled growth in the conditioning of the problem, ultimately leading to unacceptably large numerical errors.
  arXiv  Detail & Related papers  (2023-04-28T17:28:18Z)
• Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance [0.0]
  We enhance the rigour and performance of I-FENN by focusing on two crucial aspects of its PINN component. We introduce a systematic numerical approach based on a novel set of holistic performance metrics. The proposed analysis can be directly extended to other applications in science and engineering.
  arXiv  Detail & Related papers  (2023-03-03T17:39:06Z)
• 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)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Recurrent Bilinear Optimization for Binary Neural Networks [58.972212365275595]
  BNNs neglect the intrinsic bilinear relationship of real-valued weights and scale factors. Our work is the first attempt to optimize BNNs from the bilinear perspective. We obtain robust RBONNs, which show impressive performance over state-of-the-art BNNs on various models and datasets.
  arXiv  Detail & Related papers  (2022-09-04T06:45:33Z)
• Adaptive Self-supervision Algorithms for Physics-informed Neural Networks [59.822151945132525]
  Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function. We study the impact of the location of the collocation points on the trainability of these models. We propose a novel adaptive collocation scheme which progressively allocates more collocation points to areas where the model is making higher errors.
  arXiv  Detail & Related papers  (2022-07-08T18:17:06Z)
• 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 networks for continuum micromechanics [68.8204255655161]
  Recently, physics informed neural networks have successfully been applied to a broad variety of problems in applied mathematics and engineering. Due to the global approximation, physics informed neural networks have difficulties in displaying localized effects and strong non-linear solutions by optimization. It is shown, that the domain decomposition approach is able to accurately resolve nonlinear stress, displacement and energy fields in heterogeneous microstructures obtained from real-world $mu$CT-scans.
  arXiv  Detail & Related papers  (2021-10-14T14:05:19Z)

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.