Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/68344
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Applied Mathematics | en_US |
dc.creator | Guo, ZC | en_US |
dc.creator | Xiang, DH | en_US |
dc.creator | Guo, X | en_US |
dc.creator | Zhou, DX | en_US |
dc.date.accessioned | 2017-08-02T02:45:04Z | - |
dc.date.available | 2017-08-02T02:45:04Z | - |
dc.identifier.issn | 0219-5305 | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/68344 | - |
dc.language.iso | en | en_US |
dc.publisher | World Scientific | en_US |
dc.rights | Electronic 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/aa | en_US |
dc.subject | Learning theory | en_US |
dc.subject | Thresholded spectral algorithm | en_US |
dc.subject | Sparsity | en_US |
dc.subject | Learning rate | en_US |
dc.title | Thresholded spectral algorithms for sparse approximations | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 433 | en_US |
dc.identifier.epage | 455 | en_US |
dc.identifier.volume | 15 | en_US |
dc.identifier.issue | 3 | en_US |
dc.identifier.doi | 10.1142/S0219530517500026 | en_US |
dcterms.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. | en_US |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | Analysis and applications, May 2017, v. 15, no. 3, p. 433-455 | en_US |
dcterms.isPartOf | Analysis and applications | en_US |
dcterms.issued | 2017-05 | - |
dc.identifier.isi | WOS:000399796600006 | - |
dc.identifier.scopus | 2-s2.0-85017587952 | - |
dc.identifier.ros | 2016003178 | - |
dc.source.type | Article | en |
dc.identifier.eissn | 1793-6861 | en_US |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | a0101-n02, a0481-n03 | - |
dc.description.pubStatus | Published | en_US |
dc.description.oaCategory | Green (AAM) | en_US |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
empirical161222.pdf | Pre-Published version | 734.36 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.