Refined bounds for online pairwise learning algorithms

Chen, Xiaming1; Lei, Yunwen2

2018-01-31

10.1016/j.neucom.2017.11.049

NEUROCOMPUTING   影响因子和分区

0925-2312

1872-8286

Motivated by the recent growing interest in pairwise learning problems, we study the generalization performance of Online Pairwise lEaRning Algorithm (OPERA) in a reproducing kernel Hilbert space (RKHS) without an explicit regularization. The convergence rates established in this paper can be arbitrarily closed to O(T (-1/2)) within T iterations and largely improve the existing convergence rates for OPERA. Our novel analysis is conducted by showing an almost boundedness of the iterates encountered in the learning process with high probability after establishing an induction lemma on refining the RKHS norm estimate of the iterates. (C) 2017 Elsevier B.V. All rights reserved.

Pairwise learning Online learning Learning theory Reproducing Kernel Hilbert Space

SCI ; EI

英语

通讯

National Natural Science Foundation of China[11461161006] ; National Natural Science Foundation of China[11471292] ; National Natural Science Foundation of China[11771012]

Computer Science

Computer Science, Artificial Intelligence

WOS:000418370200245

ELSEVIER SCIENCE BV

20174904513606

E-learning ; Hilbert spaces ; Iterative methods ; Vector spaces

Mathematics:921 ; Numerical Methods:921.6

COMPUTER SCIENCE

Web of Science

1.City Univ Hong Kong, Dept Math, Kowloon, Hong Kong, Peoples R China
2.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China

Chen, Xiaming,Lei, Yunwen. Refined bounds for online pairwise learning algorithms[J]. NEUROCOMPUTING,2018,275:2656-2665.

Chen, Xiaming,&Lei, Yunwen.(2018).Refined bounds for online pairwise learning algorithms.NEUROCOMPUTING,275,2656-2665.

Chen, Xiaming,et al."Refined bounds for online pairwise learning algorithms".NEUROCOMPUTING 275(2018):2656-2665.