Saved in:
Bibliographic Details
Main Authors: Huang, Chutian, Ma, Chang, Wang, Kaibo, Xiang, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.06472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911366085869568
author Huang, Chutian
Ma, Chang
Wang, Kaibo
Xiang, Yang
author_facet Huang, Chutian
Ma, Chang
Wang, Kaibo
Xiang, Yang
contents Learning solution operators for differential equations with neural networks has shown great potential in scientific computing, but ensuring their stability under input perturbations remains a critical challenge. This paper presents a robust self-supervised neural operator framework that enhances stability through adversarial training while preserving accuracy. We formulate operator learning as a min-max optimization problem, where the model is trained against worst-case input perturbations to achieve consistent performance under both normal and adversarial conditions. We demonstrate that our method not only achieves good performance on standard inputs, but also maintains high fidelity under adversarial perturbed inputs. The results highlight the importance of stability-aware training in operator learning and provide a foundation for developing reliable neural PDE solvers in real-world applications, where input noise and uncertainties are inevitable.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06472
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle StablePDENet: Enhancing Stability of Operator Learning for Solving Differential Equations
Huang, Chutian
Ma, Chang
Wang, Kaibo
Xiang, Yang
Machine Learning
Learning solution operators for differential equations with neural networks has shown great potential in scientific computing, but ensuring their stability under input perturbations remains a critical challenge. This paper presents a robust self-supervised neural operator framework that enhances stability through adversarial training while preserving accuracy. We formulate operator learning as a min-max optimization problem, where the model is trained against worst-case input perturbations to achieve consistent performance under both normal and adversarial conditions. We demonstrate that our method not only achieves good performance on standard inputs, but also maintains high fidelity under adversarial perturbed inputs. The results highlight the importance of stability-aware training in operator learning and provide a foundation for developing reliable neural PDE solvers in real-world applications, where input noise and uncertainties are inevitable.
title StablePDENet: Enhancing Stability of Operator Learning for Solving Differential Equations
topic Machine Learning
url https://arxiv.org/abs/2601.06472