Discretization-independent operator learning for partial differential equations

arXiv:2507.07292 · cs.LG · Submitted 2025-07-09 · Read on arXiv

cs.LG

Submitted: 2025-07-09

Updated: 2026-09-20

Comments: 41 pages, 11 figures, submitted to the Journal of Machine Learning Research

License: http://creativecommons.org/licenses/by/4.0/

The gist: We develop a new and general encode-approximate-reconstruct operator learning model that leverages learned neural representations of bases for input and output function distributions.

Terminology

Abstract

We develop a new and general encode-approximate-reconstruct operator learning model that leverages learned neural representations of bases for input and output function distributions. We introduce the concepts of numerical operator learning and discretization independence, which clarify the relationship between theoretical formulations and practical realizations of operator learning models. Our model is discretization-independent, making it particularly effective for multiresolution learning. We establish theoretical approximation guarantees, demonstrating uniform universal approximation under strong assumptions on the input functions and statistical approximation under weaker conditions. To our knowledge, this is the first comprehensive study that investigates how discretization independence enables robust and efficient multiresolution operator learning. We validate our method through extensive numerical experiments involving both local and nonlocal PDEs, including time-independent and time-dependent problems. The results show that multiresolution training significantly improves accuracy and computational efficiency. Moreover, multiresolution training further enhances empirical discretization independence.

Related papers