Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces.

Authors
Publication date
2018
Publication type
Journal Article
Summary In this paper, we study regression problems over a separable Hilbert space with the square loss, covering non-parametric regression over a reproducing kernel Hilbert space. We investigate a class of spectral/regularized algorithms, including ridge regression, principal component regression, and gradient methods. We prove optimal, high-probability convergence results in terms of variants of norms for the studied algorithms, considering a capacity assumption on the hypothesis space and a general source condition on the target function. Consequently, we obtain almost sure convergence results with optimal rates. Our results improve and generalize previous results, filling a theoretical gap for the non-attainable cases.
Publisher
Elsevier
Topics of the publication
Themes detected by scanR from retrieved publications. For more information, see https://scanr.enseignementsup-recherche.gouv.fr