Elliptic PDE learning is provably data-efficient

Author name not available (Why is that?)

Publication date: 24 February 2023

Abstract: PDE learning is an emerging field that combines physics and machine learning to recover unknown physical systems from experimental data. While deep learning models traditionally require copious amounts of training data, recent PDE learning techniques achieve spectacular results with limited data availability. Still, these results are empirical. Our work provides theoretical guarantees on the number of input-output training pairs required in PDE learning, explaining why these methods can be data-efficient. Specifically, we exploit randomized numerical linear algebra and PDE theory to derive a provably data-efficient algorithm that recovers solution operators of 3D elliptic PDEs from input-output data and achieves an exponential convergence rate with respect to the size of the training dataset with an exceptionally high probability of success.

Has companion code repository: https://github.com/nboulle/pde-learning

This page was built for publication: Elliptic PDE learning is provably data-efficient

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6427582)