A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
- Cheng, Tin Sum
- Lucchi, Aurelien
- Dokmanić, Ivan
- Kratsios, Anastasis
- Belius, David ORCID UniDistance Suisse
-
2023
Published in:
- Advances in Neural Information Processing Systems (NeurIPS) 2023. - 2023
English
Existing statistical learning guarantees for general kernel regressors often yield loose bounds when used with finite-rank kernels. Yet, finite-rank kernels naturally appear in several machine learning problems, e.g.\ when fine-tuning a pre-trained deep neural network's last layer to adapt it to a novel task when performing transfer learning. We address this gap for finite-rank kernel ridge regression (KRR) by deriving sharp non-asymptotic upper and lower bounds for the KRR test error of any finite-rank KRR. Our bounds are tighter than previously derived bounds on finite-rank KRR, and unlike comparable results, they also remain valid for any regularization parameters.
- Identifiers
-
- DOI 10.48550/ARXIV.2310.00987
- URI https://pub.orcid.org/v3.0/0000-0003-3706-043X/work/144425780
- ARK ark:/51647/srd1336033
- Persistent URL
- https://n2t.net/ark:/51647/srd1336033
Statistics
Document views: 11
File downloads:
- A-Theoretical-Analysis-of-the-Test-Error-of-Finite-Rank-Kernel-Ridge-Regression.pdf: 22