Training dynamics in physics-informed machine learning
组织者
演讲者
胡煜中
时间
2026年07月31日 15:00 至 16:00
地点
A3-1-301
线上
Zoom 204 323 0165
(BIMSA)
摘要
Physics-informed neural networks (PINNs) provide a flexible framework for solving forward and inverse problems governed by differential equations, but their training can be slow, unstable, and strongly imbalanced across different loss components.
This talk reviews recent theoretical insights into PINN training dynamics from two perspectives. First, the neural tangent kernel (NTK) framework is used to explain spectral bias and the unequal convergence rates of PDE, boundary, and data losses. Second, information bottleneck theory and the gradient signal-to-noise ratio (SNR) are introduced to describe three training stages: fitting, diffusion, and total diffusion.
This talk reviews recent theoretical insights into PINN training dynamics from two perspectives. First, the neural tangent kernel (NTK) framework is used to explain spectral bias and the unequal convergence rates of PDE, boundary, and data losses. Second, information bottleneck theory and the gradient signal-to-noise ratio (SNR) are introduced to describe three training stages: fitting, diffusion, and total diffusion.
演讲者介绍
Hu Yuzhong is a second-year PhD student in a joint program between BIMSA and academy of mathematics and systems science, CAS, under the supervision of Professor Zhang Xiaoming.