Online pairwise learning algorithms with convex loss functions

Junhong Lin, Yunwen Lei*, Bo Zhang, Ding Xuan Zhou

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

18 Citations (Scopus)

Abstract

Online pairwise learning algorithms with general convex loss functions without regularization in a Reproducing Kernel Hilbert Space (RKHS) are investigated. Under mild conditions on loss functions and the RKHS, upper bounds for the expected excess generalization error are derived in terms of the approximation error when the stepsize sequence decays polynomially. In particular, for Lipschitz loss functions such as the hinge loss, the logistic loss and the absolute-value loss, the bounds can be of order O(formula omitted) after T iterations, while for the least squares loss, the bounds can be of order O(formula omitted) In comparison with previous works for these algorithms, a broader family of convex loss functions is studied here, and refined upper bounds are obtained.

Original languageEnglish
Pages (from-to)57-70
Number of pages14
JournalInformation Sciences
Volume406-407
DOIs
Publication statusPublished - Sept 2017

Scopus Subject Areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

User-Defined Keywords

  • Learning theory
  • Online learning
  • Pairwise learning
  • Reproducing Kernel Hilbert Space

Fingerprint

Dive into the research topics of 'Online pairwise learning algorithms with convex loss functions'. Together they form a unique fingerprint.

Cite this