BIMSA >
控制理论和非线性滤波讨论班
控制理论和非线性滤波讨论班
When and why PINNs fail to train from the viewpoint of neural tangent kernel
When and why PINNs fail to train from the viewpoint of neural tangent kernel
组织者
丘成栋
演讲者
时间
2023年11月17日 22:00 至 22:30
地点
Online
摘要
In this talk, we will share several literatures about the explanation of training dynamics of Physics-informed neural network. Especially, as a uniform framework, neural tangent kernel demonstrates the dynamical behavior when width of NN goes to infinity in the single layer setting. NTK illustrates training one-layer NN with infinite width is the same as a kernel regression. As a consequence, NTK will exhibit the training weights of different parts in loss function which will provide the guidance for adaptive algorithm of revised PINN.
演讲者介绍
焦小沛,于2017年本科毕业于上海交通大学致远学院(物理班),2022年博士毕业于清华大学数学科学系,师从丘成栋教授(IEEE fellow,前美国伊利诺伊大学芝加哥分校终身教授)。先后在北京雁栖湖应用数学研究院,荷兰特文特大学从事博士后工作(导师Johannes Schmidt-Hieber教授,国际数理统计学会会士)。现研究方向包括控制理论,随机滤波,数值微分方程,物理信息深度学习。获得2025年国家青年科学基金[C类]资助。