Thresholded spectral algorithms for sparse approximations

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

39 Scopus Citations
View graph of relations

Author(s)

  • Zheng-Chu Guo
  • Dao-Hong Xiang
  • Xin Guo
  • DIng-Xuan Zhou

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)433-455
Journal / PublicationAnalysis and Applications
Volume15
Issue number3
Online published23 Feb 2017
Publication statusPublished - May 2017

Abstract

Spectral algorithms form a general framework that unifies many regularization schemes in learning theory. In this paper, we propose and analyze a class of thresholded spectral algorithms that are designed based on empirical features. Soft thresholding is adopted to achieve sparse approximations. Our analysis shows that without sparsity assumption of the regression function, the output functions of thresholded spectral algorithms are represented by empirical features with satisfactory sparsity, and the convergence rates are comparable to those of the classical spectral algorithms in the literature.

Research Area(s)

  • learning rate, Learning theory, sparsity, thresholded spectral algorithm

Citation Format(s)

Thresholded spectral algorithms for sparse approximations. / Guo, Zheng-Chu; Xiang, Dao-Hong; Guo, Xin et al.

In: Analysis and Applications, Vol. 15, No. 3, 05.2017, p. 433-455.

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