Robust Error Bounds for Vector-Valued Kernel Ridge Regression

Abstract

While kernel-based learning methods for scalar-valued functions have been extensively studied, comparatively little work considers nonlinear vector-valued operators. Such operators with vector-valued outputs, e.g., state vectors and trajectories, commonly arise in system identification problems. In this paper, we study the problem of learning a vector-valued operator under the framework of vector-valued kernel ridge regression. We assume that the outputs take values in an arbitrary Hilbert space and are corrupted by additive noise with bounded norm. Under the assumption that the unknown operator belongs to a vector-valued reproducing kernel Hilbert space, we derive a pointwise deterministic bound on the discrepancy between the kernel ridge regression estimator and the ground truth in the corresponding Hilbert space norm. Numerical simulations under two different scenarios are presented to validate the theoretical results.

Kernel-Robust Dynamics for Reaction-Diffusion Equations with Measure-Valued Delay
Lennon Shikhman
arXiv4 Sep 2026PreprintarXiv licenceFull textAnalysis & PDEs Dynamical systemsarXiv
Wasserstein Kernel Regression with Dependent Distribution-Valued Predictors: Local Recurrence, Joint Inference, and Multivariate Gaussian Geometry
Wahiba Bouabsa, Fatimah Alshahrani
Mathematics21 Oct 2026Peer-reviewedCC BY 4.0StatisticsCrossref
New hierarchical matrices for fast kernel matrix-vector products with Applications to Gaussian processes and kernel ridge regression
Ritesh Khan, Sivaram Ambikasaran
arXiv29 Oct 2026PreprintarXiv licenceFull textNumerical analysis & scientific computing StatisticsarXiv
Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression
Guangjian Zhang
arXiv2 Oct 2026PreprintarXiv licenceFull textStatisticsarXiv
Generalization Bounds via Vector-Valued L_p Correlation V_α
Mohammad Hossein Momeni Hamaneh, Mohammad Mahdi Mojahedian, Mohammad Hossein Yassaee
arXiv21 Oct 2026PreprintCC BY 4.0Full textGeneral mathematicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{wang2026robust,
  title = {{Robust Error Bounds for Vector-Valued Kernel Ridge Regression}},
  author = {Wenbin Wang and Colin N. Jones},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.19443},
  eprint = {2609.19443},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.19443},
}

RIS

TY  - UNPB
TI  - Robust Error Bounds for Vector-Valued Kernel Ridge Regression
AU  - Wenbin Wang
AU  - Colin N. Jones
PY  - 2026
DA  - 2026/09/16
PB  - arXiv
DO  - 10.48550/arxiv.2609.19443
UR  - https://arxiv.org/abs/2609.19443
AB  - While kernel-based learning methods for scalar-valued functions have been extensively studied, comparatively little work considers nonlinear vector-valued operators. Such operators with vector-valued outputs, e.g., state vectors and trajectories, commonly arise in system identification problems. In this paper, we study the problem of learning a vector-valued operator under the framework of vector-valued kernel ridge regression. We assume that the outputs take values in an arbitrary Hilbert space and are corrupted by additive noise with bounded norm. Under the assumption that the unknown operator belongs to a vector-valued reproducing kernel Hilbert space, we derive a pointwise deterministic bound on the discrepancy between the kernel ridge regression estimator and the ground truth in the corresponding Hilbert space norm. Numerical simulations under two different scenarios are presented to validate the theoretical results.
ER  -

Abstract

Related

Cite