4 papers
Nearly Optimal Approximation Rates for Deep Super ReLU Networks on Sobolev Spaces
Yahong Yang, Yue Wu, Haizhao Yang +1
This paper introduces deep super ReLU networks (DSRNs) as a method for approximating functions in Sobolev spaces measured by Sobolev norms for with $m\ge…
Learn Singularly Perturbed Solutions via Homotopy Dynamics
Chuqi Chen, Yahong Yang, Yang Xiang +1
Solving partial differential equations (PDEs) using neural networks has become a central focus in scientific machine learning. Training neural networks for singularly perturbed pro…
Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
Chuqi Chen, Yahong Yang, Yang Xiang +1
Neural network-based approaches have recently shown significant promise in solving partial differential equations (PDEs) in science and engineering, especially in scenarios featuri…
Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers
Chuqi Chen, Qixuan Zhou, Yahong Yang +2
Neural network-based methods have emerged as powerful tools for solving partial differential equations (PDEs) in scientific and engineering applications, particularly when handling…