Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.06158 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913602386001920 |
|---|---|
| author | Zhou, Zijian Yan, Zhenya |
| author_facet | Zhou, Zijian Yan, Zhenya |
| contents | In this paper, we study the neural tangent kernel (NTK) for general partial differential equations (PDEs) based on physics-informed neural networks (PINNs). As we all know, the training of an artificial neural network can be converted to the evolution of NTK. We analyze the initialization of NTK and the convergence conditions of NTK during training for general PDEs. The theoretical results show that the homogeneity of differential operators plays a crucial role for the convergence of NTK. Moreover, based on the PINNs, we validate the convergence conditions of NTK using the initial value problems of the sine-Gordon equation and the initial-boundary value problem of the KdV equation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06158 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Is the neural tangent kernel of PINNs deep learning general partial differential equations always convergent ? Zhou, Zijian Yan, Zhenya Machine Learning Mathematical Physics Pattern Formation and Solitons Computational Physics In this paper, we study the neural tangent kernel (NTK) for general partial differential equations (PDEs) based on physics-informed neural networks (PINNs). As we all know, the training of an artificial neural network can be converted to the evolution of NTK. We analyze the initialization of NTK and the convergence conditions of NTK during training for general PDEs. The theoretical results show that the homogeneity of differential operators plays a crucial role for the convergence of NTK. Moreover, based on the PINNs, we validate the convergence conditions of NTK using the initial value problems of the sine-Gordon equation and the initial-boundary value problem of the KdV equation. |
| title | Is the neural tangent kernel of PINNs deep learning general partial differential equations always convergent ? |
| topic | Machine Learning Mathematical Physics Pattern Formation and Solitons Computational Physics |
| url | https://arxiv.org/abs/2412.06158 |