Tensor completion using total variation and low-rank matrix factorization
In this paper, we study the problem of recovering a tensor with missing data. We propose a new model combining the total variation regularization and low-rank matrix factorization. A block coordinate decent (BCD) algorithm is developed to efficiently solve the proposed optimization model. We theoret...
Gespeichert in:
| Veröffentlicht in: | Information sciences 2016-01, Vol.326, p.243-257 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 257 |
|---|---|
| container_issue | |
| container_start_page | 243 |
| container_title | Information sciences |
| container_volume | 326 |
| creator | Ji, Teng-Yu Huang, Ting-Zhu Zhao, Xi-Le Ma, Tian-Hui Liu, Gang |
| description | In this paper, we study the problem of recovering a tensor with missing data. We propose a new model combining the total variation regularization and low-rank matrix factorization. A block coordinate decent (BCD) algorithm is developed to efficiently solve the proposed optimization model. We theoretically show that under some mild conditions, the algorithm converges to the coordinatewise minimizers. Experimental results are reported to demonstrate the effectiveness of the proposed model and the efficiency of the numerical scheme. |
| doi_str_mv | 10.1016/j.ins.2015.07.049 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1762110042</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0020025515005575</els_id><sourcerecordid>1762110042</sourcerecordid><originalsourceid>FETCH-LOGICAL-c396t-e5af8a387bb2e9c3374292413c6e15270588a5ac6864f7d7abe47b55628a172e3</originalsourceid><addsrcrecordid>eNp9kMtOwzAQRS0EEqXwAeyyZJNgO7GdiBWqeFSqxKasrYkzQS6pXWy3PL6etGXNaqTRPVe6h5BrRgtGmbxdFdbFglMmCqoKWjUnZMJqxXPJG3ZKJpRymlMuxDm5iHFFKa2UlBMyX6KLPmTGrzcDJutdto3WvWXJJxiyHQQLhy-4Lhv8Zx7AvWdrSMF-ZT2Y5IP9OSQuyVkPQ8Srvzslr48Py9lzvnh5ms_uF7kpG5lyFNDXUNaqbTk2pixVxRtesdJIZIIrKuoaBBhZy6pXnYIWK9UKIXkNTHEsp-Tm2LsJ_mOLMem1jQaHARz6bdRMSc7YuI-PUXaMmuBjDNjrTbBrCN-aUb3Xpld61Kb32jRVetQ2MndHBscNO4tBR2PRGexsQJN05-0_9C-fbXXE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1762110042</pqid></control><display><type>article</type><title>Tensor completion using total variation and low-rank matrix factorization</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Ji, Teng-Yu ; Huang, Ting-Zhu ; Zhao, Xi-Le ; Ma, Tian-Hui ; Liu, Gang</creator><creatorcontrib>Ji, Teng-Yu ; Huang, Ting-Zhu ; Zhao, Xi-Le ; Ma, Tian-Hui ; Liu, Gang</creatorcontrib><description>In this paper, we study the problem of recovering a tensor with missing data. We propose a new model combining the total variation regularization and low-rank matrix factorization. A block coordinate decent (BCD) algorithm is developed to efficiently solve the proposed optimization model. We theoretically show that under some mild conditions, the algorithm converges to the coordinatewise minimizers. Experimental results are reported to demonstrate the effectiveness of the proposed model and the efficiency of the numerical scheme.</description><identifier>ISSN: 0020-0255</identifier><identifier>EISSN: 1872-6291</identifier><identifier>DOI: 10.1016/j.ins.2015.07.049</identifier><language>eng</language><publisher>Elsevier Inc</publisher><subject>Algorithms ; Block coordinate descent ; Blocking ; Factorization ; Low-rank matrix factorization ; Mathematical analysis ; Mathematical models ; Optimization ; Regularization ; Tensor completion ; Tensors ; Total variation</subject><ispartof>Information sciences, 2016-01, Vol.326, p.243-257</ispartof><rights>2015 Elsevier Inc.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c396t-e5af8a387bb2e9c3374292413c6e15270588a5ac6864f7d7abe47b55628a172e3</citedby><cites>FETCH-LOGICAL-c396t-e5af8a387bb2e9c3374292413c6e15270588a5ac6864f7d7abe47b55628a172e3</cites><orcidid>0000-0001-7766-230X ; 0000-0003-2848-8477</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.ins.2015.07.049$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Ji, Teng-Yu</creatorcontrib><creatorcontrib>Huang, Ting-Zhu</creatorcontrib><creatorcontrib>Zhao, Xi-Le</creatorcontrib><creatorcontrib>Ma, Tian-Hui</creatorcontrib><creatorcontrib>Liu, Gang</creatorcontrib><title>Tensor completion using total variation and low-rank matrix factorization</title><title>Information sciences</title><description>In this paper, we study the problem of recovering a tensor with missing data. We propose a new model combining the total variation regularization and low-rank matrix factorization. A block coordinate decent (BCD) algorithm is developed to efficiently solve the proposed optimization model. We theoretically show that under some mild conditions, the algorithm converges to the coordinatewise minimizers. Experimental results are reported to demonstrate the effectiveness of the proposed model and the efficiency of the numerical scheme.</description><subject>Algorithms</subject><subject>Block coordinate descent</subject><subject>Blocking</subject><subject>Factorization</subject><subject>Low-rank matrix factorization</subject><subject>Mathematical analysis</subject><subject>Mathematical models</subject><subject>Optimization</subject><subject>Regularization</subject><subject>Tensor completion</subject><subject>Tensors</subject><subject>Total variation</subject><issn>0020-0255</issn><issn>1872-6291</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNp9kMtOwzAQRS0EEqXwAeyyZJNgO7GdiBWqeFSqxKasrYkzQS6pXWy3PL6etGXNaqTRPVe6h5BrRgtGmbxdFdbFglMmCqoKWjUnZMJqxXPJG3ZKJpRymlMuxDm5iHFFKa2UlBMyX6KLPmTGrzcDJutdto3WvWXJJxiyHQQLhy-4Lhv8Zx7AvWdrSMF-ZT2Y5IP9OSQuyVkPQ8Srvzslr48Py9lzvnh5ms_uF7kpG5lyFNDXUNaqbTk2pixVxRtesdJIZIIrKuoaBBhZy6pXnYIWK9UKIXkNTHEsp-Tm2LsJ_mOLMem1jQaHARz6bdRMSc7YuI-PUXaMmuBjDNjrTbBrCN-aUb3Xpld61Kb32jRVetQ2MndHBscNO4tBR2PRGexsQJN05-0_9C-fbXXE</recordid><startdate>20160101</startdate><enddate>20160101</enddate><creator>Ji, Teng-Yu</creator><creator>Huang, Ting-Zhu</creator><creator>Zhao, Xi-Le</creator><creator>Ma, Tian-Hui</creator><creator>Liu, Gang</creator><general>Elsevier Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-7766-230X</orcidid><orcidid>https://orcid.org/0000-0003-2848-8477</orcidid></search><sort><creationdate>20160101</creationdate><title>Tensor completion using total variation and low-rank matrix factorization</title><author>Ji, Teng-Yu ; Huang, Ting-Zhu ; Zhao, Xi-Le ; Ma, Tian-Hui ; Liu, Gang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c396t-e5af8a387bb2e9c3374292413c6e15270588a5ac6864f7d7abe47b55628a172e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Algorithms</topic><topic>Block coordinate descent</topic><topic>Blocking</topic><topic>Factorization</topic><topic>Low-rank matrix factorization</topic><topic>Mathematical analysis</topic><topic>Mathematical models</topic><topic>Optimization</topic><topic>Regularization</topic><topic>Tensor completion</topic><topic>Tensors</topic><topic>Total variation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ji, Teng-Yu</creatorcontrib><creatorcontrib>Huang, Ting-Zhu</creatorcontrib><creatorcontrib>Zhao, Xi-Le</creatorcontrib><creatorcontrib>Ma, Tian-Hui</creatorcontrib><creatorcontrib>Liu, Gang</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Information sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ji, Teng-Yu</au><au>Huang, Ting-Zhu</au><au>Zhao, Xi-Le</au><au>Ma, Tian-Hui</au><au>Liu, Gang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Tensor completion using total variation and low-rank matrix factorization</atitle><jtitle>Information sciences</jtitle><date>2016-01-01</date><risdate>2016</risdate><volume>326</volume><spage>243</spage><epage>257</epage><pages>243-257</pages><issn>0020-0255</issn><eissn>1872-6291</eissn><abstract>In this paper, we study the problem of recovering a tensor with missing data. We propose a new model combining the total variation regularization and low-rank matrix factorization. A block coordinate decent (BCD) algorithm is developed to efficiently solve the proposed optimization model. We theoretically show that under some mild conditions, the algorithm converges to the coordinatewise minimizers. Experimental results are reported to demonstrate the effectiveness of the proposed model and the efficiency of the numerical scheme.</abstract><pub>Elsevier Inc</pub><doi>10.1016/j.ins.2015.07.049</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0001-7766-230X</orcidid><orcidid>https://orcid.org/0000-0003-2848-8477</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0020-0255 |
| ispartof | Information sciences, 2016-01, Vol.326, p.243-257 |
| issn | 0020-0255 1872-6291 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1762110042 |
| source | Elsevier ScienceDirect Journals Complete |
| subjects | Algorithms Block coordinate descent Blocking Factorization Low-rank matrix factorization Mathematical analysis Mathematical models Optimization Regularization Tensor completion Tensors Total variation |
| title | Tensor completion using total variation and low-rank matrix factorization |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T21%3A01%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Tensor%20completion%20using%20total%20variation%20and%20low-rank%20matrix%20factorization&rft.jtitle=Information%20sciences&rft.au=Ji,%20Teng-Yu&rft.date=2016-01-01&rft.volume=326&rft.spage=243&rft.epage=257&rft.pages=243-257&rft.issn=0020-0255&rft.eissn=1872-6291&rft_id=info:doi/10.1016/j.ins.2015.07.049&rft_dat=%3Cproquest_cross%3E1762110042%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1762110042&rft_id=info:pmid/&rft_els_id=S0020025515005575&rfr_iscdi=true |