Cauchy Random Features for Operator Learning in Sobolev Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Chunyang, Needell, Deanna, Schaeffer, Hayden
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916943290695680
author Liao, Chunyang
Needell, Deanna
Schaeffer, Hayden
author_facet Liao, Chunyang
Needell, Deanna
Schaeffer, Hayden
contents Operator learning is the approximation of operators between infinite dimensional Banach spaces using machine learning approaches. While most progress in this area has been driven by variants of deep neural networks such as the Deep Operator Network and Fourier Neural Operator, the theoretical guarantees are often in the form of a universal approximation property. However, the existence theorems do not guarantee that an accurate operator network is obtainable in practice. Motivated by the recent kernel-based operator learning framework, we propose a random feature operator learning method with theoretical guarantees and error bounds. The random feature method can be viewed as a randomized approximation of a kernel method, which significantly reduces the computation requirements for training. We provide a generalization error analysis for our proposed random feature operator learning method along with comprehensive numerical results. Compared to kernel-based method and neural network methods, the proposed method can obtain similar or better test errors across benchmarks examples with significantly reduced training times. An additional advantages it that our implementation is simple and does require costly computational resources, such as GPU.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00300
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cauchy Random Features for Operator Learning in Sobolev Space
Liao, Chunyang
Needell, Deanna
Schaeffer, Hayden
Machine Learning
Numerical Analysis
Operator learning is the approximation of operators between infinite dimensional Banach spaces using machine learning approaches. While most progress in this area has been driven by variants of deep neural networks such as the Deep Operator Network and Fourier Neural Operator, the theoretical guarantees are often in the form of a universal approximation property. However, the existence theorems do not guarantee that an accurate operator network is obtainable in practice. Motivated by the recent kernel-based operator learning framework, we propose a random feature operator learning method with theoretical guarantees and error bounds. The random feature method can be viewed as a randomized approximation of a kernel method, which significantly reduces the computation requirements for training. We provide a generalization error analysis for our proposed random feature operator learning method along with comprehensive numerical results. Compared to kernel-based method and neural network methods, the proposed method can obtain similar or better test errors across benchmarks examples with significantly reduced training times. An additional advantages it that our implementation is simple and does require costly computational resources, such as GPU.
title Cauchy Random Features for Operator Learning in Sobolev Space
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2503.00300