Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSs

It is known that more and more mathematicians have paid their attention to the field of learning with a Banach space since Banach spaces may provide abundant inner-product structures. We give investigations on the convergence of a kernel-regularized online binary classification learning algorithm in...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin Liu, Xiaoling Pan, Baohuai Sheng
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Journal of Mathematics
Online Access:http://dx.doi.org/10.1155/2023/6566375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850175000496046080
author Lin Liu
Xiaoling Pan
Baohuai Sheng
author_facet Lin Liu
Xiaoling Pan
Baohuai Sheng
author_sort Lin Liu
collection DOAJ
description It is known that more and more mathematicians have paid their attention to the field of learning with a Banach space since Banach spaces may provide abundant inner-product structures. We give investigations on the convergence of a kernel-regularized online binary classification learning algorithm in the setting of reproducing kernel Banach spaces (RKBSs), design an online iteration algorithm with the subdifferential of the norm and the logistic loss, and provide an upper bound for the learning rate, which shows that the online learning algorithm converges if RKBSs satisfy 2-uniform convexity.
format Article
id doaj-art-d741697bb1eb4927b61ce2d1d8a2ffc8
institution OA Journals
issn 2314-4785
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Journal of Mathematics
spelling doaj-art-d741697bb1eb4927b61ce2d1d8a2ffc82025-08-20T02:19:33ZengWileyJournal of Mathematics2314-47852023-01-01202310.1155/2023/6566375Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSsLin Liu0Xiaoling Pan1Baohuai Sheng2School of Mathematical Physics and InformationSchool of Mathematical Physics and InformationSchool of Mathematical Physics and InformationIt is known that more and more mathematicians have paid their attention to the field of learning with a Banach space since Banach spaces may provide abundant inner-product structures. We give investigations on the convergence of a kernel-regularized online binary classification learning algorithm in the setting of reproducing kernel Banach spaces (RKBSs), design an online iteration algorithm with the subdifferential of the norm and the logistic loss, and provide an upper bound for the learning rate, which shows that the online learning algorithm converges if RKBSs satisfy 2-uniform convexity.http://dx.doi.org/10.1155/2023/6566375
spellingShingle Lin Liu
Xiaoling Pan
Baohuai Sheng
Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSs
Journal of Mathematics
title Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSs
title_full Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSs
title_fullStr Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSs
title_full_unstemmed Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSs
title_short Theory Analysis for the Convergence of Kernel-Regularized Online Binary Classification Learning Associated with RKBSs
title_sort theory analysis for the convergence of kernel regularized online binary classification learning associated with rkbss
url http://dx.doi.org/10.1155/2023/6566375
work_keys_str_mv AT linliu theoryanalysisfortheconvergenceofkernelregularizedonlinebinaryclassificationlearningassociatedwithrkbss
AT xiaolingpan theoryanalysisfortheconvergenceofkernelregularizedonlinebinaryclassificationlearningassociatedwithrkbss
AT baohuaisheng theoryanalysisfortheconvergenceofkernelregularizedonlinebinaryclassificationlearningassociatedwithrkbss