EUVIMEDEUVIMED entdecken
Crossref

Fine-Grained Analysis of Nonparametric Estimation for Pairwise Learning

Junyu Zhou, Shuo Huang, Han Feng, Puyu Wang, Ding-Xuan Zhou

IEEE Transactions on Neural Networks and Learning Systems · 2026-09 · 37 (9) · 4219-4230

DOI: 10.1109/tnnls.2026.3661550 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2026-09. Verfasst von Junyu Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: University of Sydney, Alexander von Humboldt-Stiftung, Australian Research Council through Discovery.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this article, we are concerned with the generalization performance of nonparametric estimation for pairwise learning. Most of the existing work requires the hypothesis space to be convex or a VC-class, and the loss to be convex. However, these restrictive assumptions limit the applicability of the results in studying many popular methods, especially kernel methods and neural networks. We significantly relax these restrictive assumptions and establish a sharp oracle inequality of the empirical minimizer with a general hypothesis space for the Lipschitz continuous pairwise losses. As an example, we apply our general results to study pairwise least squares regression and derive an excess population risk bound that matches the minimax lower bound for the pointwise least squares regression. The key novelty lies in constructing a structured deep ReLU neural network to approximate the true predictor, and in designing a targeted hypothesis space composed of networks with this structure and controllable complexity. Experiments validate the effectiveness of the proposed method. This example demonstrates that the obtained general results indeed help us to explore the generalization performance on a variety of problems that cannot be handled by existing approaches.

Förderung

  • University of Sydney
  • Alexander von Humboldt-Stiftung
  • Australian Research Council through Discovery

Zitieren

APA

Zhou, J., Huang, S., Feng, H., Wang, P., & Zhou, D. X. (2026). Fine-Grained Analysis of Nonparametric Estimation for Pairwise Learning. IEEE Transactions on Neural Networks and Learning Systems, 37(9), 4219-4230. https://doi.org/10.1109/tnnls.2026.3661550

Vancouver

Zhou J, Huang S, Feng H, Wang P, Zhou DX. Fine-Grained Analysis of Nonparametric Estimation for Pairwise Learning. IEEE Transactions on Neural Networks and Learning Systems. 2026;37(9):4219-4230. doi:10.1109/tnnls.2026.3661550

BibTeX
@article{Zhou2026,
  author = {Zhou, Junyu and Huang, Shuo and Feng, Han and Wang, Puyu and Zhou, Ding-Xuan},
  title = {Fine-Grained Analysis of Nonparametric Estimation for Pairwise Learning},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2026},
  volume = {37},
  number = {9},
  pages = {4219--4230},
  doi = {10.1109/tnnls.2026.3661550}
}
Kostenlos starten →