Concentration estimates for learning with unbounded sampling

Download PDF
Open Webpage

Zheng-Chu Guo, Ding-Xuan Zhou

Published: 2013, Last Modified: 12 May 2025Adv. Comput. Math. 2013EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: The least-square regression problem is considered by regularization schemes in reproducing kernel Hilbert spaces. The learning algorithm is implemented with samples drawn from unbounded sampling processes. The purpose of this paper is to present concentration estimates for the error based on ℓ2-empirical covering numbers, which improves learning rates in the literature.