Yuxiang Zhao

collaborators

2 papers

math.NA2026

Energy Dissipation Preserving Feature-based DNN Galerkin Methods for Gradient Flows

Tao Tang, Jiang Yang, Yuxiang Zhao +1

In recent years, deep learning methods, exemplified by Physics-Informed Neural Networks (PINNs), have been widely applied to the numerical solution of differential equations. Howev…

cs.LG2025

$I^µ$ -rank and the Staircase Phenomenon: New Insights into Neural Network Training Dynamics

Jiang Yang, Yuxiang Zhao, Quanhui Zhu

Understanding the training dynamics of deep neural networks (DNNs), particularly how they evolve low-dimensional features from high-dimensional data, remains a central challenge in…

Energy Dissipation Preserving Feature-based DNN Galerkin Methods for Gradient Flows

I^µ-rank and the Staircase Phenomenon: New Insights into Neural Network Training Dynamics

$I^µ$ -rank and the Staircase Phenomenon: New Insights into Neural Network Training Dynamics