Sparse multiple kernel learning : Minimax rates with random projection

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Article number106142
Journal / PublicationJournal of Statistical Planning and Inference
Volume231
Online published27 Dec 2023
Publication statusPublished - Jul 2024

Abstract

In kernel-based learning, the random projection method, also called random sketching, has been successfully used in kernel ridge regression to reduce the computational burden in the big data setting, and at the same time retain the minimax convergence rate. In this work, we consider its use in sparse multiple kernel learning problems where a closed-form optimizer is not available, which poses significant technical challenges, for which the existing results do not carry over directly. Even when random projection is not used, our risk bound improves on the existing results in several aspects. We also illustrate the use of random projection via some numerical examples. © 2023 Elsevier B.V.

Research Area(s)

  • Convergence rate, Kernel method, Random projection, Reproducing kernel Hilbert space

Citation Format(s)

Sparse multiple kernel learning: Minimax rates with random projection. / Lu, Wenqi; Zhu, Zhongyi; Li, Rui et al.
In: Journal of Statistical Planning and Inference, Vol. 231, 106142, 07.2024.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review