Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jia-Qi, Shi, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915956603748352
author Yang, Jia-Qi
Shi, Lei
author_facet Yang, Jia-Qi
Shi, Lei
contents We consider a class of statistical inverse problems involving the estimation of a regression operator from a Polish space to a separable Hilbert space, where the target lies in a vector-valued reproducing kernel Hilbert space induced by an operator-valued kernel. To address the associated ill-posedness, we analyze regularized stochastic gradient descent (SGD) algorithms in both online and finite-horizon settings. The former uses polynomially decaying step sizes and regularization parameters, while the latter adopts fixed values. Under suitable structural and distributional assumptions, we establish dimension-independent bounds for prediction and estimation errors. The resulting convergence rates are near-optimal in expectation, and we also derive high-probability estimates that imply almost sure convergence. Our analysis introduces a general technique for obtaining high-probability guarantees in infinite-dimensional settings. We illustrate the practical scope of our framework with applications to structured prediction and parametric PDEs, providing examples that reflect how the approach can be applied in practice.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18184
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels
Yang, Jia-Qi
Shi, Lei
Machine Learning
Functional Analysis
Statistics Theory
We consider a class of statistical inverse problems involving the estimation of a regression operator from a Polish space to a separable Hilbert space, where the target lies in a vector-valued reproducing kernel Hilbert space induced by an operator-valued kernel. To address the associated ill-posedness, we analyze regularized stochastic gradient descent (SGD) algorithms in both online and finite-horizon settings. The former uses polynomially decaying step sizes and regularization parameters, while the latter adopts fixed values. Under suitable structural and distributional assumptions, we establish dimension-independent bounds for prediction and estimation errors. The resulting convergence rates are near-optimal in expectation, and we also derive high-probability estimates that imply almost sure convergence. Our analysis introduces a general technique for obtaining high-probability guarantees in infinite-dimensional settings. We illustrate the practical scope of our framework with applications to structured prediction and parametric PDEs, providing examples that reflect how the approach can be applied in practice.
title Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels
topic Machine Learning
Functional Analysis
Statistics Theory
url https://arxiv.org/abs/2504.18184