Accelerating cross-validation with total variation and its application to super-resolution imaging

We develop an approximation formula for the cross-validation error (CVE) of a sparse linear regression penalized by ℓ1-norm and total variation terms, which is based on a perturbative expansion utilizing the largeness of both the data dimensionality and the model. The developed formula allows us to...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2017-12, Vol.12 (12), p.e0188012-e0188012
Main Authors: Obuchi, Tomoyuki, Ikeda, Shiro, Akiyama, Kazunori, Kabashima, Yoshiyuki
Format: Article
Language:English
Subjects:
Computer and Information Sciences
Physical Sciences
Resampling (Statistics)
Research and Analysis Methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c750t-b947891fdd61d2848bbb4160ada61970f8b76f26fc565c112dc9fc0433dd870d3
cites cdi_FETCH-LOGICAL-c750t-b947891fdd61d2848bbb4160ada61970f8b76f26fc565c112dc9fc0433dd870d3
container_end_page e0188012
container_issue 12
container_start_page e0188012
container_title PloS one
container_volume 12
creator Obuchi, Tomoyuki
Ikeda, Shiro
Akiyama, Kazunori
Kabashima, Yoshiyuki
description We develop an approximation formula for the cross-validation error (CVE) of a sparse linear regression penalized by ℓ1-norm and total variation terms, which is based on a perturbative expansion utilizing the largeness of both the data dimensionality and the model. The developed formula allows us to reduce the necessary computational cost of the CVE evaluation significantly. The practicality of the formula is tested through application to simulated black-hole image reconstruction on the event-horizon scale with super resolution. The results demonstrate that our approximation reproduces the CVE values obtained via literally conducted cross-validation with reasonably good precision.
doi_str_mv 10.1371/journal.pone.0188012
format article
fullrecord <record><control><sourceid>gale_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_4e707dde93d046ebbd7b82a20695a743</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A517829152</galeid><doaj_id>oai_doaj_org_article_4e707dde93d046ebbd7b82a20695a743</doaj_id><sourcerecordid>A517829152</sourcerecordid><originalsourceid>FETCH-LOGICAL-c750t-b947891fdd61d2848bbb4160ada61970f8b76f26fc565c112dc9fc0433dd870d3</originalsourceid><addsrcrecordid>eNqNkl2L1DAUhoso7jr6D0QKgqwXHZO0-ejNwrCsOrCw4NdtSJO0kyHT1CQd9d-bmc4uU_BCetHy9jlP29M3y15DsIQlhR-2bvS9sMvB9XoJIGMAoifZJaxLVBAEyqdn1xfZixC2AOCSEfI8u0A1ggRBfJk1Kym11V5E03e59C6EYi-sUSlwff7LxE0eXRQ23wtvplD0Kjcx5GIYrJFTFl0exkH7wuvg7HjMzE50yfoye9YKG_Sr03mRff94--3mc3F3_2l9s7orJMUgFk1dUVbDVikCFWIVa5qmggQIJQisKWhZQ0mLSCsxwRJCpGTdSlCVpVKMAlUusvXkVU5s-eDT4_0f7oThx8D5jgsfjbSaV5oCqpSuSwUqoptG0YYhgQCpsaBJuciuJ9cwNjutpO6jF3Ymnd_pzYZ3bs8xRYASlARXJ4F3P0cdIt-ZkDZtRa_dGHj6IgxgzUqW0LcT2on0aqZvXTLKA85XGFKGaogPwuU_qHQovTMydaA1KZ8NvJ8NJCbq37ETYwh8_fXL_7P3P-bsuzN2o4WNm4dfHuZgNYHHVnndPq4PAn6oMD9VmB8qzE8VTmNvzlf_OPTQ2fIvOYPvHQ</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1975019838</pqid></control><display><type>article</type><title>Accelerating cross-validation with total variation and its application to super-resolution imaging</title><source>Open Access: PubMed Central</source><source>Publicly Available Content Database</source><creator>Obuchi, Tomoyuki ; Ikeda, Shiro ; Akiyama, Kazunori ; Kabashima, Yoshiyuki</creator><contributor>Wang, Yuanquan</contributor><creatorcontrib>Obuchi, Tomoyuki ; Ikeda, Shiro ; Akiyama, Kazunori ; Kabashima, Yoshiyuki ; Wang, Yuanquan</creatorcontrib><description>We develop an approximation formula for the cross-validation error (CVE) of a sparse linear regression penalized by ℓ1-norm and total variation terms, which is based on a perturbative expansion utilizing the largeness of both the data dimensionality and the model. The developed formula allows us to reduce the necessary computational cost of the CVE evaluation significantly. The practicality of the formula is tested through application to simulated black-hole image reconstruction on the event-horizon scale with super resolution. The results demonstrate that our approximation reproduces the CVE values obtained via literally conducted cross-validation with reasonably good precision.</description><identifier>ISSN: 1932-6203</identifier><identifier>EISSN: 1932-6203</identifier><identifier>DOI: 10.1371/journal.pone.0188012</identifier><identifier>PMID: 29216215</identifier><language>eng</language><publisher>United States: Public Library of Science</publisher><subject>Computer and Information Sciences ; Physical Sciences ; Resampling (Statistics) ; Research and Analysis Methods</subject><ispartof>PloS one, 2017-12, Vol.12 (12), p.e0188012-e0188012</ispartof><rights>COPYRIGHT 2017 Public Library of Science</rights><rights>2017 Obuchi et al 2017 Obuchi et al</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c750t-b947891fdd61d2848bbb4160ada61970f8b76f26fc565c112dc9fc0433dd870d3</citedby><cites>FETCH-LOGICAL-c750t-b947891fdd61d2848bbb4160ada61970f8b76f26fc565c112dc9fc0433dd870d3</cites><orcidid>0000-0003-1216-489X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC5720762/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC5720762/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,37013,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29216215$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><contributor>Wang, Yuanquan</contributor><creatorcontrib>Obuchi, Tomoyuki</creatorcontrib><creatorcontrib>Ikeda, Shiro</creatorcontrib><creatorcontrib>Akiyama, Kazunori</creatorcontrib><creatorcontrib>Kabashima, Yoshiyuki</creatorcontrib><title>Accelerating cross-validation with total variation and its application to super-resolution imaging</title><title>PloS one</title><addtitle>PLoS One</addtitle><description>We develop an approximation formula for the cross-validation error (CVE) of a sparse linear regression penalized by ℓ1-norm and total variation terms, which is based on a perturbative expansion utilizing the largeness of both the data dimensionality and the model. The developed formula allows us to reduce the necessary computational cost of the CVE evaluation significantly. The practicality of the formula is tested through application to simulated black-hole image reconstruction on the event-horizon scale with super resolution. The results demonstrate that our approximation reproduces the CVE values obtained via literally conducted cross-validation with reasonably good precision.</description><subject>Computer and Information Sciences</subject><subject>Physical Sciences</subject><subject>Resampling (Statistics)</subject><subject>Research and Analysis Methods</subject><issn>1932-6203</issn><issn>1932-6203</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNqNkl2L1DAUhoso7jr6D0QKgqwXHZO0-ejNwrCsOrCw4NdtSJO0kyHT1CQd9d-bmc4uU_BCetHy9jlP29M3y15DsIQlhR-2bvS9sMvB9XoJIGMAoifZJaxLVBAEyqdn1xfZixC2AOCSEfI8u0A1ggRBfJk1Kym11V5E03e59C6EYi-sUSlwff7LxE0eXRQ23wtvplD0Kjcx5GIYrJFTFl0exkH7wuvg7HjMzE50yfoye9YKG_Sr03mRff94--3mc3F3_2l9s7orJMUgFk1dUVbDVikCFWIVa5qmggQIJQisKWhZQ0mLSCsxwRJCpGTdSlCVpVKMAlUusvXkVU5s-eDT4_0f7oThx8D5jgsfjbSaV5oCqpSuSwUqoptG0YYhgQCpsaBJuciuJ9cwNjutpO6jF3Ymnd_pzYZ3bs8xRYASlARXJ4F3P0cdIt-ZkDZtRa_dGHj6IgxgzUqW0LcT2on0aqZvXTLKA85XGFKGaogPwuU_qHQovTMydaA1KZ8NvJ8NJCbq37ETYwh8_fXL_7P3P-bsuzN2o4WNm4dfHuZgNYHHVnndPq4PAn6oMD9VmB8qzE8VTmNvzlf_OPTQ2fIvOYPvHQ</recordid><startdate>20171207</startdate><enddate>20171207</enddate><creator>Obuchi, Tomoyuki</creator><creator>Ikeda, Shiro</creator><creator>Akiyama, Kazunori</creator><creator>Kabashima, Yoshiyuki</creator><general>Public Library of Science</general><general>Public Library of Science (PLoS)</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>IOV</scope><scope>ISR</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-1216-489X</orcidid></search><sort><creationdate>20171207</creationdate><title>Accelerating cross-validation with total variation and its application to super-resolution imaging</title><author>Obuchi, Tomoyuki ; Ikeda, Shiro ; Akiyama, Kazunori ; Kabashima, Yoshiyuki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c750t-b947891fdd61d2848bbb4160ada61970f8b76f26fc565c112dc9fc0433dd870d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer and Information Sciences</topic><topic>Physical Sciences</topic><topic>Resampling (Statistics)</topic><topic>Research and Analysis Methods</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Obuchi, Tomoyuki</creatorcontrib><creatorcontrib>Ikeda, Shiro</creatorcontrib><creatorcontrib>Akiyama, Kazunori</creatorcontrib><creatorcontrib>Kabashima, Yoshiyuki</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Gale In Context: Opposing Viewpoints</collection><collection>Gale In Context: Science</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>PloS one</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Obuchi, Tomoyuki</au><au>Ikeda, Shiro</au><au>Akiyama, Kazunori</au><au>Kabashima, Yoshiyuki</au><au>Wang, Yuanquan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Accelerating cross-validation with total variation and its application to super-resolution imaging</atitle><jtitle>PloS one</jtitle><addtitle>PLoS One</addtitle><date>2017-12-07</date><risdate>2017</risdate><volume>12</volume><issue>12</issue><spage>e0188012</spage><epage>e0188012</epage><pages>e0188012-e0188012</pages><issn>1932-6203</issn><eissn>1932-6203</eissn><abstract>We develop an approximation formula for the cross-validation error (CVE) of a sparse linear regression penalized by ℓ1-norm and total variation terms, which is based on a perturbative expansion utilizing the largeness of both the data dimensionality and the model. The developed formula allows us to reduce the necessary computational cost of the CVE evaluation significantly. The practicality of the formula is tested through application to simulated black-hole image reconstruction on the event-horizon scale with super resolution. The results demonstrate that our approximation reproduces the CVE values obtained via literally conducted cross-validation with reasonably good precision.</abstract><cop>United States</cop><pub>Public Library of Science</pub><pmid>29216215</pmid><doi>10.1371/journal.pone.0188012</doi><tpages>e0188012</tpages><orcidid>https://orcid.org/0000-0003-1216-489X</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1932-6203
ispartof PloS one, 2017-12, Vol.12 (12), p.e0188012-e0188012
issn 1932-6203
1932-6203
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_4e707dde93d046ebbd7b82a20695a743
source Open Access: PubMed Central; Publicly Available Content Database
subjects Computer and Information Sciences
Physical Sciences
Resampling (Statistics)
Research and Analysis Methods
title Accelerating cross-validation with total variation and its application to super-resolution imaging
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-30T23%3A37%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Accelerating%20cross-validation%20with%20total%20variation%20and%20its%20application%20to%20super-resolution%20imaging&rft.jtitle=PloS%20one&rft.au=Obuchi,%20Tomoyuki&rft.date=2017-12-07&rft.volume=12&rft.issue=12&rft.spage=e0188012&rft.epage=e0188012&rft.pages=e0188012-e0188012&rft.issn=1932-6203&rft.eissn=1932-6203&rft_id=info:doi/10.1371/journal.pone.0188012&rft_dat=%3Cgale_doaj_%3EA517829152%3C/gale_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c750t-b947891fdd61d2848bbb4160ada61970f8b76f26fc565c112dc9fc0433dd870d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1975019838&rft_id=info:pmid/29216215&rft_galeid=A517829152&rfr_iscdi=true