Refined bounds for online pairwise learning algorithms

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 arbitr...

Full description

Saved in:
Bibliographic Details
Published inNeurocomputing (Amsterdam) Vol. 275; pp. 2656 - 2665
Main Authors Chen, Xiaming, Lei, Yunwen
Format Journal Article
LanguageEnglish
Published Elsevier B.V 31.01.2018
Subjects
Learning theory
Online learning
Pairwise learning
Reproducing Kernel Hilbert Space
Pairwise learning
Learning theory
Online learning
Reproducing Kernel Hilbert Space
Online AccessGet full text

Cover

More Information
Summary: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−12) 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.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2017.11.049