Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/68344
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Applied Mathematicsen_US
dc.creatorGuo, ZCen_US
dc.creatorXiang, DHen_US
dc.creatorGuo, Xen_US
dc.creatorZhou, DXen_US
dc.date.accessioned2017-08-02T02:45:04Z-
dc.date.available2017-08-02T02:45:04Z-
dc.identifier.issn0219-5305en_US
dc.identifier.urihttp://hdl.handle.net/10397/68344-
dc.language.isoenen_US
dc.publisherWorld Scientificen_US
dc.rightsElectronic version of an article published as Analysis and Applications, vol. 15, no. 3, 2017, p. 433-455, https://doi.org/10.1142/S0219530517500026, © World Scientific Publishing Company, https://www.worldscientific.com/worldscinet/aaen_US
dc.subjectLearning theoryen_US
dc.subjectThresholded spectral algorithmen_US
dc.subjectSparsityen_US
dc.subjectLearning rateen_US
dc.titleThresholded spectral algorithms for sparse approximationsen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage433en_US
dc.identifier.epage455en_US
dc.identifier.volume15en_US
dc.identifier.issue3en_US
dc.identifier.doi10.1142/S0219530517500026en_US
dcterms.abstractSpectral 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.en_US
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitationAnalysis and applications, May 2017, v. 15, no. 3, p. 433-455en_US
dcterms.isPartOfAnalysis and applicationsen_US
dcterms.issued2017-05-
dc.identifier.isiWOS:000399796600006-
dc.identifier.scopus2-s2.0-85017587952-
dc.identifier.ros2016003178-
dc.source.typeArticleen
dc.identifier.eissn1793-6861en_US
dc.description.oaAccepted Manuscripten_US
dc.identifier.FolderNumbera0101-n02, a0481-n03en_US
dc.description.pubStatusPublisheden_US
Appears in Collections:Journal/Magazine Article
Files in This Item:
File Description SizeFormat 
empirical161222.pdfPre-Published version734.36 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Final Accepted Manuscript
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

Page views

350
Last Week
3
Last month
Citations as of Nov 22, 2023

Downloads

108
Citations as of Nov 22, 2023

SCOPUSTM   
Citations

41
Last Week
0
Last month
Citations as of Dec 1, 2023

WEB OF SCIENCETM
Citations

41
Last Week
0
Last month
Citations as of Nov 30, 2023

Google ScholarTM

Check

Altmetric


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