Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/98631
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Applied Mathematicsen_US
dc.creatorYuan, Yen_US
dc.creatorSun, Den_US
dc.creatorToh, KCen_US
dc.date.accessioned2023-05-10T02:00:46Z-
dc.date.available2023-05-10T02:00:46Z-
dc.identifier.issn2640-3498en_US
dc.identifier.urihttp://hdl.handle.net/10397/98631-
dc.description35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, 10-15 July 2018en_US
dc.language.isoenen_US
dc.publisherPMLR web siteen_US
dc.rightsCopyright 2018 by the author(s)en_US
dc.rightsPosted with permission of the author.en_US
dc.titleAn efficient semismooth Newton based algorithm for convex clusteringen_US
dc.typeConference Paperen_US
dc.identifier.spage5718en_US
dc.identifier.epage5726en_US
dc.identifier.volume80en_US
dcterms.abstractClustering is a fundamental problem in unsupervised learning. Popular methods like K-means, may suffer from instability as they are prone to get stuck in its local minima. Recently, the sumof-norms (SON) model (also known as clustering path), which is a convex relaxation of hierarchical clustering model, has been proposed in (Lindsten et al., 2011) and (Hocking et al., 2011). Although numerical algorithms like alternating direction method of multipliers (ADMM) and alternating minimization algorithm (AMA) have been proposed to solve convex clustering model (Chi & Lange, 2015), it is known to be very challenging to solve large-scale problems. In this paper, we propose a semismooth Newton based augmented Lagrangian method for large-scale convex clustering problems. Extensive numerical experiments on both simulated and real data demonstrate that our algorithm is highly efficient and robust for solving large-scale problems. Moreover, the numerical results also show the superior performance and scalability of our algorithm comparing to existing first-order methods.en_US
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitationProceedings of Machine Learning Research, 2018, v. 80, p. 5718-5726en_US
dcterms.isPartOfProceedings of Machine Learning Researchen_US
dcterms.issued2018-
dc.identifier.scopus2-s2.0-85057264119-
dc.relation.conferenceInternational Conference on Machine Learning [ICML]en_US
dc.description.validate202305 bcchen_US
dc.description.oaVersion of Recorden_US
dc.identifier.FolderNumbera0339-n02, AMA-0434-
dc.description.fundingSourceSelf-fundeden_US
dc.description.pubStatusPublisheden_US
dc.identifier.OPUS20280297-
dc.description.oaCategoryCopyright retained by authoren_US
Appears in Collections:Conference Paper
Files in This Item:
File Description SizeFormat 
yuan18a.pdf599.66 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

Page views

98
Citations as of Jul 14, 2024

Downloads

19
Citations as of Jul 14, 2024

SCOPUSTM   
Citations

2
Citations as of Jun 21, 2024

Google ScholarTM

Check


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