Generalization Limits of In-Context Operator Networks for Higher-Order Partial Differential Equations

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mahowald, Jamie, Bui-Thanh, Tan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914414250164224
author Mahowald, Jamie
Bui-Thanh, Tan
author_facet Mahowald, Jamie
Bui-Thanh, Tan
contents We investigate the generalization capabilities of In-Context Operator Networks (ICONs), a new class of operator networks that build on the principles of in-context learning, for higher-order partial differential equations. We extend previous work by expanding the type and scope of differential equations handled by the foundation model. We demonstrate that while processing complex inputs requires some new computational methods, the underlying machine learning techniques are largely consistent with simpler cases. Our implementation shows that although point-wise accuracy degrades for higher-order problems like the heat equation, the model retains qualitative accuracy in capturing solution dynamics and overall behavior. This demonstrates the model's ability to extrapolate fundamental solution characteristics to problems outside its training regime.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21534
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generalization Limits of In-Context Operator Networks for Higher-Order Partial Differential Equations
Mahowald, Jamie
Bui-Thanh, Tan
Machine Learning
Numerical Analysis
We investigate the generalization capabilities of In-Context Operator Networks (ICONs), a new class of operator networks that build on the principles of in-context learning, for higher-order partial differential equations. We extend previous work by expanding the type and scope of differential equations handled by the foundation model. We demonstrate that while processing complex inputs requires some new computational methods, the underlying machine learning techniques are largely consistent with simpler cases. Our implementation shows that although point-wise accuracy degrades for higher-order problems like the heat equation, the model retains qualitative accuracy in capturing solution dynamics and overall behavior. This demonstrates the model's ability to extrapolate fundamental solution characteristics to problems outside its training regime.
title Generalization Limits of In-Context Operator Networks for Higher-Order Partial Differential Equations
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2603.21534