JMLR

Optimal Convergence Rates for Neural Operators

Authors
Mike Nguyen Nicole Mücke
Paper Information
  • Journal:
    Journal of Machine Learning Research
  • Added to Tracker:
    Sep 08, 2026
Abstract

We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive fast convergence rates that are known to be minimax optimal within the framework of non-parametric regression in reproducing kernel Hilbert spaces (RKHS). We provide bounds on the number of hidden neurons and the number of second-stage samples necessary for generalization. To justify our NTK regime, we additionally show that any operator approximable by a neural operator can also be approximated by an operator from the RKHS. A key application of neural operators is learning surrogate maps for the solution operators of partial differential equations (PDEs). We consider the standard Poisson equation to illustrate our theoretical findings with simulations.

Author Details
Mike Nguyen
Author
Nicole Mücke
Author
Citation Information
APA Format
Mike Nguyen & Nicole Mücke . Optimal Convergence Rates for Neural Operators. Journal of Machine Learning Research .
BibTeX Format
@article{paper1620,
  title = { Optimal Convergence Rates for Neural Operators },
  author = { Mike Nguyen and Nicole Mücke },
  journal = { Journal of Machine Learning Research },
  url = { https://www.jmlr.org/papers/v27/25-0507.html }
}