Learning Discontinuous Galerkin Solutions to Elliptic Problems via Small Linear Convolutional Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915149254754304 |
|---|---|
| author | Celaya, Adrian Wang, Yimo Fuentes, David Riviere, Beatrice |
| author_facet | Celaya, Adrian Wang, Yimo Fuentes, David Riviere, Beatrice |
| contents | In recent years, there has been an increasing interest in using deep learning and neural networks to tackle scientific problems, particularly in solving partial differential equations (PDEs). However, many neural network-based methods, such as physics-informed neural networks, depend on automatic differentiation and the sampling of collocation points, which can result in a lack of interpretability and lower accuracy compared to traditional numerical methods. To address this issue, we propose two approaches for learning discontinuous Galerkin solutions to PDEs using small linear convolutional neural networks. Our first approach is supervised and depends on labeled data, while our second approach is unsupervised and does not rely on any training data. In both cases, our methods use substantially fewer parameters than similar numerics-based neural networks while also demonstrating comparable accuracy to the true and DG solutions for elliptic problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08783 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Discontinuous Galerkin Solutions to Elliptic Problems via Small Linear Convolutional Neural Networks Celaya, Adrian Wang, Yimo Fuentes, David Riviere, Beatrice Machine Learning Numerical Analysis In recent years, there has been an increasing interest in using deep learning and neural networks to tackle scientific problems, particularly in solving partial differential equations (PDEs). However, many neural network-based methods, such as physics-informed neural networks, depend on automatic differentiation and the sampling of collocation points, which can result in a lack of interpretability and lower accuracy compared to traditional numerical methods. To address this issue, we propose two approaches for learning discontinuous Galerkin solutions to PDEs using small linear convolutional neural networks. Our first approach is supervised and depends on labeled data, while our second approach is unsupervised and does not rely on any training data. In both cases, our methods use substantially fewer parameters than similar numerics-based neural networks while also demonstrating comparable accuracy to the true and DG solutions for elliptic problems. |
| title | Learning Discontinuous Galerkin Solutions to Elliptic Problems via Small Linear Convolutional Neural Networks |
| topic | Machine Learning Numerical Analysis |
| url | https://arxiv.org/abs/2502.08783 |