ISCAS OpenIR
maximum volume clustering
Gang Niu; Bo Dai; Lin Shang; Masashi Sugiyama
2011
Conference Name14th International Conference on Artificial Intelligence and Statistics, AISTATS 2011
SourceJournal of Machine Learning Research
Pages561-569
Conference DateApril 11, 2011 - April 13, 2011
Conference PlaceFort Lauderdale, FL, United states
Indexed TypeEI
ISSN1532-4435
Department(1) Department of Computer Science Tokyo Institute of Technology Japan; (2) State Key Laboratory for Novel Software Technology Nanjing University China; (3) NLPR/LIAMA Institute of Automation Chinese Academy of Science China
English AbstractThe large volume principle proposed by Vladimir Vapnik, which advocates that hypotheses lying in an equivalence class with a larger volume are more preferable, is a useful alternative to the large margin principle. In this paper, we introduce a clustering model based on the large volume principle called maximum volume clustering (MVC), and propose two algorithms to solve it approximately: a soft-label and a hard-labelMVC algorithms based on sequential quadratic programming and semi-definite programming, respectively. Our MVC model includes spectral clustering and maximum margin clustering as special cases, and is substantially more general. We also establish the finite sample stability and an error bound for soft-label MVC method. Experiments show that the proposed MVC approach compares favorably with state-of-the-art clustering algorithms. Copyright 2011 by the authors.; The large volume principle proposed by Vladimir Vapnik, which advocates that hypotheses lying in an equivalence class with a larger volume are more preferable, is a useful alternative to the large margin principle. In this paper, we introduce a clustering model based on the large volume principle called maximum volume clustering (MVC), and propose two algorithms to solve it approximately: a soft-label and a hard-labelMVC algorithms based on sequential quadratic programming and semi-definite programming, respectively. Our MVC model includes spectral clustering and maximum margin clustering as special cases, and is substantially more general. We also establish the finite sample stability and an error bound for soft-label MVC method. Experiments show that the proposed MVC approach compares favorably with state-of-the-art clustering algorithms. Copyright 2011 by the authors.
KeywordArtificial Intelligence Clustering Algorithms Equivalence Classes Sampling
SponsorshipGoogle; Microsoft; PASCAL2; IBM; NEC - Epowered by Innovation
Language英语
Content Type会议论文
URIhttp://ir.iscas.ac.cn/handle/311060/16311
Collection中国科学院软件研究所
Recommended Citation
GB/T 7714
Gang Niu,Bo Dai,Lin Shang,et al. maximum volume clustering[C],2011:561-569.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gang Niu]'s Articles
[Bo Dai]'s Articles
[Lin Shang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gang Niu]'s Articles
[Bo Dai]'s Articles
[Lin Shang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gang Niu]'s Articles
[Bo Dai]'s Articles
[Lin Shang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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