You are not logged in.

Lingo: linearized grassmannian optimization for nuclear norm minimization

Li, Qian, Niu, Wenjia, Li, Gang, Cao, Yanan, Tan, Jianlong and Guo, Li 2015, Lingo: linearized grassmannian optimization for nuclear norm minimization, in CIKM 2015: Proceedings of the 24th ACM International Conference on Information and Knowledge Management, ACM: The Association for Computing Machinery, New York, N.Y., pp. 801-809, doi: 10.1145/2806416.2806532.

Attached Files
Name Description MIMEType Size Downloads

Title Lingo: linearized grassmannian optimization for nuclear norm minimization
Author(s) Li, Qian
Niu, Wenjia
Li, GangORCID iD for Li, Gang orcid.org/0000-0003-1583-641X
Cao, Yanan
Tan, Jianlong
Guo, Li
Conference name ACM International Conference on Information and Knowledge Management (24th : 2015 : Melbourne, Victoria)
Conference location Melbourne, Victoria
Conference dates 19-23 Oct. 2015
Title of proceedings CIKM 2015: Proceedings of the 24th ACM International Conference on Information and Knowledge Management
Publication date 2015
Start page 801
End page 809
Total pages 9
Publisher ACM: The Association for Computing Machinery
Place of publication New York, N.Y.
Keyword(s) low-rank
nuclear norm
matrix completion
Grassmannian
Summary As a popular heuristic to the matrix rank minimization problem, nuclear norm minimization attracts intensive research attentions. Matrix factorization based algorithms can reduce the expensive computation cost of SVD for nuclear norm minimization. However, most matrix factorization based algorithms fail to provide the theoretical guarantee for convergence caused by their non-unique factorizations. This paper proposes an efficient and accurate Linearized Grass-mannian Optimization (Lingo) algorithm, which adopts matrix factorization and Grassmann manifold structure to alternatively minimize the subproblems. More specially, linearization strategy makes the auxiliary variables unnecessary and guarantees the close-form solution for low periteration complexity. Lingo then converts linearized objective function into a nuclear norm minimization over Grass-mannian manifold, which could remedy the non-unique of solution for the low-rank matrix factorization. Extensive comparison experiments demonstrate the accuracy and efficiency of Lingo algorithm. The global convergence of Lingo is guaranteed with theoretical proof, which also verifies the effectiveness of Lingo.
ISBN 9781450337946
Language eng
DOI 10.1145/2806416.2806532
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2015, The Association for Computing Machinery
Persistent URL http://hdl.handle.net/10536/DRO/DU:30082015

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 87 Abstract Views, 0 File Downloads  -  Detailed Statistics
Created: Tue, 08 Mar 2016, 14:34:18 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.