Thresholded spectral algorithms for sparse approximations

Zheng Chu Guo, Dao Hong Xiang, Xin Guo, DIng Xuan Zhou

Research output: Journal article publicationJournal articleAcademic researchpeer-review

29 Citations (Scopus)

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.
Original languageEnglish
Pages (from-to)433-455
Number of pages23
JournalAnalysis and Applications
Volume15
Issue number3
DOIs
Publication statusPublished - 1 May 2017

Keywords

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

ASJC Scopus subject areas

  • Analysis
  • Applied Mathematics

Cite this