Kernel reconstruction learning

doi:10.1016/j.neucom.2022.12.015

	Kernel reconstruction learning
	Wu, Yun 1,2; Xiong, Shifeng 2
刊名	NEUROCOMPUTING
	2023-02-14
卷号	522 页码:1-10
关键词	Kernel method Representer theorem Interpolation Classification Density estimation Sequential algorithm
ISSN号	0925-2312
DOI	10.1016/j.neucom.2022.12.015
英文摘要	This paper proposes a class of kernel interpolation-based methods, called kernel reconstruction learning, for solving machine learning problems. Kernel reconstruction learning uses kernel interpolators to recon-struct the unknown functions, which are needed to estimate in the problem, with estimated function val-ues at selected knots. It can be applied to any learning problem that involves function estimation. We prove a reconstruction representer theorem, which indicates that conventional kernel methods, including kernel ridge regression, kernel support vector machine, and kernel logistic regression, can be viewed as special cases of kernel reconstruction learning. Furthermore, kernel reconstruction learning provides new algorithms for large datasets. The kernel reconstruction vector machine, kernel reconstruction logistic regression, and kernel reconstruction density estimation are discussed in detail. With appropriate imple-mentations, they are shown to have higher prediction/estimation accuracy and/or less computational cost than popular kernel methods.(c) 2022 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China ; [12171462]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000904832400001
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/60458]
专题	中国科学院数学与系统科学研究院
通讯作者	Xiong, Shifeng
作者单位	1.Univ Chinese Acad Sci, Sch Math Sci, Beijing, Peoples R China 2.Chinese Acad Sci, Acad Math & Syst Sci, NCMIS, KLSC, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Wu, Yun,Xiong, Shifeng. Kernel reconstruction learning[J]. NEUROCOMPUTING,2023,522:1-10.
APA	Wu, Yun,&Xiong, Shifeng.(2023).Kernel reconstruction learning.NEUROCOMPUTING,522,1-10.
MLA	Wu, Yun,et al."Kernel reconstruction learning".NEUROCOMPUTING 522(2023):1-10.