arXiv Machine Learning By Yuezhou Ma, Haixu Wu, Hang Zhou, Huikun Weng, Jianmin Wang, Mingsheng Long

ProPINN: Demystifying Propagation Failures in Physics-Informed Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2502. 00803v3 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) have earned high expectations in solving partial differential equations (PDEs), but their optimization usually faces thorny challenges due to the unique derivative-dependent loss function.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jun 3

PINNfluence: Interpreting PINNs through Influence Functions

arXiv:2409. 08958v3 Announce Type: replace-cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful deep learning approach for solving partial differential equations (PDEs) in the physical sciences, yet their behavior remains largely opaque and is typically understood through failure mode analyses rather than explicit interpretability.

By Aleksander Krasowski, Jonas R. Naujoks, Moritz Weckbecker, Galip \"U. Yolcu, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek, Ren\'e P. Klausen
arXiv Machine Learning
Aug 10

Mitigating Gradient Pathology in PINNs through Aligned Constraint

arXiv:2605. 25001v2 Announce Type: replace Abstract: While Physics-Informed Neural Networks (PINNs) are powerful for solving Partial Differential Equations (PDEs), their training is often paralyzed by gradient pathology.

By Yichen Luo, Peiyu Zhu, Dongxiao Hu, Jia Wang, Tailin Wu, Dapeng Lan, Yu Liu, Zhibo Pang