Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916972723175424 |
|---|---|
| author | Bylinkin, Dmitry Aleksandrov, Mikhail Chezhegov, Savelii Beznosikov, Aleksandr |
| author_facet | Bylinkin, Dmitry Aleksandrov, Mikhail Chezhegov, Savelii Beznosikov, Aleksandr |
| contents | Physics-informed neural networks (PINNs) have gained prominence in recent years and are now effectively used in a number of applications. However, their performance remains unstable due to the complex landscape of the loss function. To address this issue, we reformulate PINN training as a nonconvex-strongly concave saddle-point problem. After establishing the theoretical foundation for this approach, we conduct an extensive experimental study, evaluating its effectiveness across various tasks and architectures. Our results demonstrate that the proposed method outperforms the current state-of-the-art techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16008 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation Bylinkin, Dmitry Aleksandrov, Mikhail Chezhegov, Savelii Beznosikov, Aleksandr Machine Learning Optimization and Control Physics-informed neural networks (PINNs) have gained prominence in recent years and are now effectively used in a number of applications. However, their performance remains unstable due to the complex landscape of the loss function. To address this issue, we reformulate PINN training as a nonconvex-strongly concave saddle-point problem. After establishing the theoretical foundation for this approach, we conduct an extensive experimental study, evaluating its effectiveness across various tasks and architectures. Our results demonstrate that the proposed method outperforms the current state-of-the-art techniques. |
| title | Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2507.16008 |