Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/68344
Title: Thresholded spectral algorithms for sparse approximations
Authors: Guo, ZC
Xiang, DH
Guo, X 
Zhou, DX
Keywords: Learning theory
Thresholded spectral algorithm
Sparsity
Learning rate
Issue Date: May-2017
Publisher: World Scientific
Source: Analysis and applications, May 2017, v. 15, no. 3, p. 433-455 How to cite?
Journal: Analysis and applications 
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.
URI: http://hdl.handle.net/10397/68344
ISSN: 0219-5305
EISSN: 1793-6861
DOI: 10.1142/S0219530517500026
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

WEB OF SCIENCETM
Citations

1
Citations as of Aug 3, 2017

Page view(s)

74
Checked on Aug 20, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.