FastVPINNs: A Fast, Versatile and Robust Variational PINNs Framework for Forward and Inverse Problems in Science
Abstract
Variational physics-informed neural networks (VPINNs), with h- and p-refinement, show promise over conventional PINNs. But existing frameworks are computationally inefficient and unable to deal with complex meshes. As such, VPINNs have had limited application when it comes to practical problems in science and engineering. In the present work, we propose a novel VPINNs framework, that achieves up to a 100x speed-up over SOTA codes. We demonstrate the flexibility of this framework by solving different forward and inverse problems on complex geometries, and by applying VPINNs to vector-valued partial differential equations.
Cite
Text
Ghose et al. "FastVPINNs: A Fast, Versatile and Robust Variational PINNs Framework for Forward and Inverse Problems in Science." ICLR 2024 Workshops: AI4DiffEqtnsInSci, 2024.Markdown
[Ghose et al. "FastVPINNs: A Fast, Versatile and Robust Variational PINNs Framework for Forward and Inverse Problems in Science." ICLR 2024 Workshops: AI4DiffEqtnsInSci, 2024.](https://mlanthology.org/iclrw/2024/ghose2024iclrw-fastvpinns/)BibTeX
@inproceedings{ghose2024iclrw-fastvpinns,
title = {{FastVPINNs: A Fast, Versatile and Robust Variational PINNs Framework for Forward and Inverse Problems in Science}},
author = {Ghose, Divij and Anandh, Thivin and Ganesan, Sashikumaar},
booktitle = {ICLR 2024 Workshops: AI4DiffEqtnsInSci},
year = {2024},
url = {https://mlanthology.org/iclrw/2024/ghose2024iclrw-fastvpinns/}
}