Online regularized classification algorithms

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

87 Scopus Citations
View graph of relations

Author(s)

  • Yiming Ying
  • Ding-Xuan Zhou

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)4775-4788
Journal / PublicationIEEE Transactions on Information Theory
Volume52
Issue number11
Publication statusPublished - Nov 2006

Abstract

This paper considers online classification learning algorithms based on regularization schemes in reproducing kernel Hilbert spaces associated with general convex loss functions. A novel capacity independent approach is presented. It verifies the strong convergence of the algorithm under a very weak assumption of the step sizes and yields satisfactory convergence rates for polynomially decaying step sizes. Explicit learning rates with respect to the misclassification error are given in terms of the choice of step sizes and the regularization parameter (depending on the sample size). Error bounds associated with the hinge loss, the least square loss, and the support vector machine q-norm loss are presented to illustrate our method. © 2006 IEEE.

Research Area(s)

  • Classification algorithm, Error analysis, Online learning, Regularization, Reproducing kernel Hilbert spaces

Citation Format(s)

Online regularized classification algorithms. / Ying, Yiming; Zhou, Ding-Xuan.
In: IEEE Transactions on Information Theory, Vol. 52, No. 11, 11.2006, p. 4775-4788.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review