📢 Active Learning for Neural PDE Solvers (AL4PDE; arxiv.org/abs/2408.01536) While active learning is common in other domains, it has yet to be studied extensively for neural PDE solving. This work introduces AL4PDE, a modular and extensible active learning benchmark. #ML4PDE
Includes multiple parametric PDEs & SOTA surrogate models for a solver-in-the-loop setting, enabling the evaluation of existing & development of new active learning methods for PDE solving. Evaluates batch active learning algorithms such as uncertainty & feature-based methods.
Shows that active learning reduces the average error by up to 71% compared to random sampling & significantly reduces worst-case errors. Acquired datasets are reusable, providing benefits for surrogate models not involved in the data generation. Code and dataset available soon.
A new line of research towards developing algorithms & methods that enable neural operators to achieve generalization over desiderata such as PDE parameters, ICs, BCs, Geometries, Resolutions, etc. #NeuralOperators #ML4Science #PDEs #NumericalSolvers #ActiveLearning #AI4Science
United States Xu hướng
- 1. Jets 82.7K posts
- 2. Bengals 49.3K posts
- 3. Eagles 112K posts
- 4. Giants 94.1K posts
- 5. Caleb 37.1K posts
- 6. Falcons 38.4K posts
- 7. Zac Taylor 5,023 posts
- 8. Browns 47.1K posts
- 9. Bears 66K posts
- 10. Myles Garrett 8,365 posts
- 11. Ravens 50.5K posts
- 12. Dolphins 28K posts
- 13. Drake Maye 16.6K posts
- 14. 49ers 30.9K posts
- 15. Skattebo 44K posts
- 16. Andy Dalton 9,077 posts
- 17. Justin Fields 7,908 posts
- 18. Anthony Nelson 1,280 posts
- 19. Sam Williams N/A
- 20. Dylan Harper 4,794 posts
Something went wrong.
Something went wrong.