Some Best Practices in Operator Learning

Dustin Enyeart, Guang Lin
12/9/2024
cs.LGphysics.comp-ph

No confident code implementation found for this paper.

Abstract

Hyperparameters searches are computationally expensive. This paper studies some general choices of hyperparameters and training methods specifically for operator learning. It considers the architectures DeepONets, Fourier neural operators and Koopman autoencoders for several differential equations to find robust trends. Some options considered are activation functions, dropout and stochastic weight averaging.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A short tour of operator learning theory: Convergence rates, statistical limits, and open questions

82% match2026

HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork

82% match2026

Towards Gaussian Process for operator learning: an uncertainty aware resolution independent operator learning algorithm for computational mechanics

81% match2024

Operator Learning: A Statistical Perspective

81% match2025

The Parametric Complexity of Operator Learning

81% match2023

Spectral bias in physics-informed and operator learning: Analysis and mitigation guidelines

81% match1 repo52026

Cite this paper

@article{enyeart2024some,
  title  = {Some Best Practices in Operator Learning},
  author = {Dustin Enyeart and Guang Lin},
  year   = {2024},
  eprint = {2412.06686},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.06686v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.06686.svg)](https://codeofpaper.com/paper/2412.06686)

Discussion