Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces

Yahong Yang; Zecheng Zhang; Wei Zhu; Wenjing Liao; Hao Liu

cs.LGJun 16, 2026

Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces

Authors: Yahong Yang, Zecheng Zhang, Wei Zhu, Wenjing Liao, Hao Liu

Organizations: School of Mathematics, Georgia Institute of Technology, 686 Cherry Street, Atlanta, GA 30332-0160, USA. · Department of Applied and Computational Mathematics and Statistics, University of Notre Dame, Notre Dame, IN 46556, USA. · Department of Mathematics, Hong Kong Baptist University, FSC1202, Fong Shu Chuen Building, Hong Kong Baptist University, Kowloon Tong, Hong Kong.

Abstract

We develop approximation and generalization error estimates for multi-input neural operators, with the output error measured in Sobolev norms. In contrast to standard operator-learning settings with a single input function, our framework allows multiple input functions defined on possibly different domains, with different dimensions and Sobolev regularities. The derived rates explicitly quantify the contribution of each input space to the final error bound. In particular, in the balanced regime, the approximation and generalization rates are governed by the interaction between the input dimensions, regularities, and Sobolev orders, while the dependence on the model complexity retains a $\log\log/\log$ -type structure. Our analysis provides a general theoretical framework for multi-input operator learning, including Sobolev training, and is applicable to operator learning problems arising from partial differential equations and scientific computing.

Explore similar work

Quantitative Sobolev Approximation Bounds for Neural Operators with Empirical Validation on Burgers Equation
May 4, 2026Nicole HaoLogarithmic Sobolev Inequalities Fourier Neural Operators
Kernel Methods for Learning Operators with Multiple Inputs and Outputs
Aug 12, 2026Adrien Weihs, Chunyang Liao, Jingmin Sun +1Probabilistic Operator Learning Kernel Method
Near-Optimal Learning of Gaussian Sobolev Operators
Jul 8, 2026Ben Adcock, Michael Griebel, Gregor MaierLogarithmic Sobolev Inequalities Probabilistic Operator Learning

May 4, 2026 · cs.LGJ/K move · Enter open · S save

Quantitative Sobolev Approximation Bounds for Neural Operators with Empirical Validation on Burgers Equation

Nicole Hao

Department of Mathematics, Cornell University

Neural operators have emerged as a powerful tool for learning mappings between infinite-dimensional function spaces. However, their approximation properties in Sobolev norms remain poorly quantified, even though these norms control both function values and derivatives and are the natural metrics for PDE well-posedness, stability, and generalization. We develop a functional-analytic framework for operator learning in Sobolev spaces and connect it to the numerical behavior of Fourier Neural Operators (FNOs) on a prototypical PDE. First, for a continuous nonlinear operator

\mathcal{G}: H^{s}(D)\to H^{t}(D')

with

s > d/2

and inputs restricted to a compact subset of

H^{s}(D)

, we prove that

\mathcal{G}

can be uniformly approximated in

H^{t}

-norm by a neural operator with

\mathcal{O}(\varepsilon^{-d/s})

trainable parameters. This yields an explicit complexity--error relation of the form

\|\mathcal{G}-\mathcal{G}_θ\|_{H^{t}} \lesssim C N^{-s/d}

. We then study the one-dimensional viscous Burgers solution operator

\mathcal{G}: u_{0}\mapsto u(\cdot,1)

on a bounded

H^{1}

-ball and train FNOs with an

H^{1}

-loss. Across a sweep of model sizes, we obtain test

H^{1}

-errors down to

\mathcal{O}(10^{-7})

and relative errors of order

10^{-3}

, with predictions accurately matching both solutions and spatial derivatives on held-out data. A log-log plot of Sobolev error versus parameter count exhibits an approximate power law

\|\mathcal{G}-\mathcal{G}_θ\|_{H^{1}} \approx C N^{-α}

with empirical exponent

α\approx 1.4

, and long-horizon training reveals optimization instabilities in large FNOs, providing quantitative evidence that Sobolev-space approximation theory meaningfully predicts neural-operator scaling behavior.

Logarithmic Sobolev Inequalities Fourier Neural Operators Neural Operators Neural-Network Approximation Spectral Norm Loss Function Empirical Study

Open paper Ask about it PDF

Abstract

Explore similar work

Quantitative Sobolev Approximation Bounds for Neural Operators with Empirical Validation on Burgers Equation

Kernel Methods for Learning Operators with Multiple Inputs and Outputs

Near-Optimal Learning of Gaussian Sobolev Operators