File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Regularized semi-supervised least squares regression with dependent samples

TitleRegularized semi-supervised least squares regression with dependent samples
Authors
Tong, HongzhiNg, Michael
KeywordsSemi-supervised learning
Regularization
Non-iid sampling
Least squares regression
Issue Date2018
Citation
Communications in Mathematical Sciences, 2018, v. 16, n. 5, p. 1347-1360 How to Cite?
DOI: http://dx.doi.org/10.4310/CMS.2018.v16.n5.a08
Abstract© 2018 International Press. In this paper, we study regularized semi-supervised least squares regression with dependent samples. We analyze the regularized algorithm based on reproducing kernel Hilbert spaces, and show, with the use of unlabelled data that the regularized least squares algorithm can achieve the nearly minimax optimal learning rate with a logarithmic term for dependent samples. Our new results are better than existing results in the literature.
Persistent Identifierhttp://hdl.handle.net/10722/276625
ISSN
1539-6746
2023 Impact Factor: 1.2
2023 SCImago Journal Rankings: 0.756

 

DC FieldValueLanguage
dc.contributor.authorTong, Hongzhi-
dc.contributor.authorNg, Michael-
dc.date.accessioned2019-09-18T08:34:10Z-
dc.date.available2019-09-18T08:34:10Z-
dc.date.issued2018-
dc.identifier.citationCommunications in Mathematical Sciences, 2018, v. 16, n. 5, p. 1347-1360-
dc.identifier.issn1539-6746-
dc.identifier.urihttp://hdl.handle.net/10722/276625-
dc.description.abstract© 2018 International Press. In this paper, we study regularized semi-supervised least squares regression with dependent samples. We analyze the regularized algorithm based on reproducing kernel Hilbert spaces, and show, with the use of unlabelled data that the regularized least squares algorithm can achieve the nearly minimax optimal learning rate with a logarithmic term for dependent samples. Our new results are better than existing results in the literature.-
dc.languageeng-
dc.relation.ispartofCommunications in Mathematical Sciences-
dc.subjectSemi-supervised learning-
dc.subjectRegularization-
dc.subjectNon-iid sampling-
dc.subjectLeast squares regression-
dc.titleRegularized semi-supervised least squares regression with dependent samples-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.4310/CMS.2018.v16.n5.a08-
dc.identifier.scopuseid_2-s2.0-85059263251-
dc.identifier.volume16-
dc.identifier.issue5-
dc.identifier.spage1347-
dc.identifier.epage1360-
dc.identifier.eissn1945-0796-
dc.identifier.issnl1539-6746-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats