A Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learning
Not on the map. Why?
Abstract (arXiv)
We develop a stochastic approximation framework for learning nonlinear operators between infinite-dimensional spaces utilizing general Mercer operator-valued kernels. Our framework encompasses two key classes: (i) operator-valued kernels whose associated integral operators are compact and hence admit discrete spectral decompositions, and (ii) separable kernels of the form K(x,x')=k(x,x')T, where k is a scalar-valued kernel and T is a positive operator on the output space. This broad setting induces expressive vector-valued reproducing kernel Hilbert spaces (RKHSs) that generalize the classical K=kI paradigm, thereby enabling rich structural modeling with rigorous theoretical guarantees. To address target operators lying outside the RKHS, we introduce vector-valued interpolation spaces to precisely quantify misspecification error. Within this framework, we establish non-asymptotic convergence rates for prediction, estimation, and misspecification errors in the online and finite-horizon settings. Importantly, the framework also accommodates a range of operator learning settings, from Fredholm integral operators to encoder--decoder architectures. Numerical experiments on the two-dimensional Navier--Stokes equations illustrate the proposed approach.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 48 references that are in the map. First posted on arXiv 14 Sep 2025.
Builds on
28 of 48 references.
References · 28
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2020Model Reduction and Neural Networks for Parametric PDEscited by 258
- 2019Kernel Instrumental Variable Regressioncited by 118
- 2017Sobolev Norm Learning Rates for Regularized Least-Squares Algorithmcited by 114
- 2020A Measure-Theoretic Approach to Kernel Conditional Mean Embeddingscited by 86
- 2024Operator Learning: Algorithms and Analysiscited by 85
- 2022Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spacescited by 67
- 2015Operator-valued Kernels for Learning from Functional Response Datacited by 60
- 2021Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restrictioncited by 55
- 2022Optimally tackling covariate shift in RKHS-based nonparametric regressioncited by 54
- 2023Kernel Methods are Competitive for Operator Learningcited by 50
16 more
- 2022Deep Nonparametric Estimation of Operators between Infinite Dimensional Spacescited by 45
- 2020A General Framework for Consistent Structured Prediction with Implicit Loss Embeddingscited by 35
- 2016A Consistent Regularization Approach for Structured Predictioncited by 33
- 2022Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problemcited by 28
- 2023Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithmcited by 22
- 2025Operator Learning: A Statistical Perspectivecited by 17
- 2024Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithmscited by 12
- 2022Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descentcited by 11
- 2022Capacity dependent analysis for functional online learning algorithmscited by 10
- 2024Optimal Convergence Rates for Neural Operatorscited by 8
- 2025Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysiscited by 7
- 2022Vector-Valued Least-Squares Regression under Output Regularity Assumptionscited by 5
- 2024Neural Operators for Nonlinear Functionals on RKHScited by 5
- 2024Stochastic Gradient Descent for Operator Learning in Hilbert Spaces: Convergence Rates and Minimax Lower Boundscited by 2
- 2024Structured Prediction in Online Learningcited by 2
- 2025Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernelscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.