<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01229023v2</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-20T05:09:56+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Fast clustering for scalable statistical analysis on structured images</title>
            <author role="aut">
              <persName>
                <forename type="first">Bertrand</forename>
                <surname>Thirion</surname>
              </persName>
              <idno type="idhal" notation="numeric">760493</idno>
              <idno type="halauthorid" notation="string">142896-760493</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5018-7895</idno>
              <idno type="IDREF">https://www.idref.fr/080779565</idno>
              <affiliation ref="#struct-56051"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Andrés</forename>
                <surname>Hoyos-Idrobo</surname>
              </persName>
              <email type="md5">349a23df60a224a682e30e411567b53a</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">andres-hoyos-idrobo</idno>
              <idno type="idhal" notation="numeric">14413</idno>
              <idno type="halauthorid" notation="string">26245-14413</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1729-1927</idno>
              <idno type="IDREF">https://www.idref.fr/200864912</idno>
              <affiliation ref="#struct-40417"/>
              <affiliation ref="#struct-56051"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jonas</forename>
                <surname>Kahn</surname>
              </persName>
              <email type="md5">f42af55fd041b4eee720ec710782cc61</email>
              <email type="domain">phare.normalesup.org</email>
              <idno type="idhal" notation="string">jonas-kahn</idno>
              <idno type="idhal" notation="numeric">740469</idno>
              <idno type="halauthorid" notation="string">11331-740469</idno>
              <idno type="IDREF">https://www.idref.fr/175857075</idno>
              <idno type="ORCID">https://orcid.org/0009-0003-8947-7111</idno>
              <affiliation ref="#struct-32"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gaël</forename>
                <surname>Varoquaux</surname>
              </persName>
              <email type="md5">5c9fb379c4e97b58960d74dcbfc5dee5</email>
              <email type="domain">normalesup.org</email>
              <idno type="idhal" notation="string">gael-varoquaux</idno>
              <idno type="idhal" notation="numeric">5878</idno>
              <idno type="halauthorid" notation="string">8362-5878</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1076-5122</idno>
              <idno type="IDREF">https://www.idref.fr/126239894</idno>
              <affiliation ref="#struct-40417"/>
              <affiliation ref="#struct-56051"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Bertrand</forename>
                <surname>Thirion</surname>
              </persName>
              <email type="md5">7e13f0e43798e8f4736d80bff2fa694a</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-37875"/>
            <funder ref="#projeurop-129603"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2015-11-16 10:17:58</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2016-04-11 09:31:53</date>
              <date type="whenWritten">2015-05-01</date>
              <date type="whenModified">2026-02-06 11:36:02</date>
              <date type="whenReleased">2016-04-11 11:55:42</date>
              <date type="whenProduced">2015-07-10</date>
              <date type="whenEndEmbargoed">2016-04-11</date>
              <ref type="file" target="https://inria.hal.science/hal-01229023v2/document">
                <date notBefore="2016-04-11"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01229023v2/file/paper.pdf" id="file-1300448-1380352">
                <date notBefore="2016-04-11"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1511.04898"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="145919">
                <persName>
                  <forename>Bertrand</forename>
                  <surname>Thirion</surname>
                </persName>
                <email type="md5">7e13f0e43798e8f4736d80bff2fa694a</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01229023</idno>
            <idno type="halUri">https://inria.hal.science/hal-01229023</idno>
            <idno type="halBibtex">thirion:hal-01229023</idno>
            <idno type="halRefHtml">&lt;i&gt;ICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015)&lt;/i&gt;, Bertrand Thirion, Lars Kai Hansen, Sanmi Koyejo, Jul 2015, Lille, France</idno>
            <idno type="halRef">ICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015), Bertrand Thirion, Lars Kai Hansen, Sanmi Koyejo, Jul 2015, Lille, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1300448-1380352"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CEA">CEA - Commissariat à l'énergie atomique</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-SACLAY" corresp="INRIA">INRIA Saclay - Ile de France</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="CEA-UPSAY" corresp="CEA">CEA - Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="CEA-UPSAY-SACLAY" corresp="CEA">CEA-UPSAY-SACLAY</idno>
            <idno type="stamp" n="INRIA-SACLAY-2015" corresp="UNIV-PARIS-SACLAY">INRIA-SACLAY-2015</idno>
            <idno type="stamp" n="JOLIOT" corresp="CEA">Institut des Sciences du Vivant Frédéric JOLIOT</idno>
            <idno type="stamp" n="CEA-DRF" corresp="CEA">Direction de Recherche Fondamentale</idno>
            <idno type="stamp" n="NEUROSPIN" corresp="JOLIOT">Département NEUROSPIN</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="GS-ENGINEERING">Graduate School Sciences de l'Ingénierie et des Systèmes</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="LPP-MATH">Laboratoire Paul Painlevé (UMR8524)</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Fast clustering for scalable statistical analysis on structured images</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Bertrand</forename>
                    <surname>Thirion</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">760493</idno>
                  <idno type="halauthorid" notation="string">142896-760493</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5018-7895</idno>
                  <idno type="IDREF">https://www.idref.fr/080779565</idno>
                  <affiliation ref="#struct-56051"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Andrés</forename>
                    <surname>Hoyos-Idrobo</surname>
                  </persName>
                  <email type="md5">349a23df60a224a682e30e411567b53a</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">andres-hoyos-idrobo</idno>
                  <idno type="idhal" notation="numeric">14413</idno>
                  <idno type="halauthorid" notation="string">26245-14413</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1729-1927</idno>
                  <idno type="IDREF">https://www.idref.fr/200864912</idno>
                  <affiliation ref="#struct-40417"/>
                  <affiliation ref="#struct-56051"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jonas</forename>
                    <surname>Kahn</surname>
                  </persName>
                  <email type="md5">f42af55fd041b4eee720ec710782cc61</email>
                  <email type="domain">phare.normalesup.org</email>
                  <idno type="idhal" notation="string">jonas-kahn</idno>
                  <idno type="idhal" notation="numeric">740469</idno>
                  <idno type="halauthorid" notation="string">11331-740469</idno>
                  <idno type="IDREF">https://www.idref.fr/175857075</idno>
                  <idno type="ORCID">https://orcid.org/0009-0003-8947-7111</idno>
                  <affiliation ref="#struct-32"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gaël</forename>
                    <surname>Varoquaux</surname>
                  </persName>
                  <email type="md5">5c9fb379c4e97b58960d74dcbfc5dee5</email>
                  <email type="domain">normalesup.org</email>
                  <idno type="idhal" notation="string">gael-varoquaux</idno>
                  <idno type="idhal" notation="numeric">5878</idno>
                  <idno type="halauthorid" notation="string">8362-5878</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1076-5122</idno>
                  <idno type="IDREF">https://www.idref.fr/126239894</idno>
                  <affiliation ref="#struct-40417"/>
                  <affiliation ref="#struct-56051"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015)</title>
                  <date type="start">2015-07-10</date>
                  <date type="end">2015-07-10</date>
                  <settlement>Lille</settlement>
                  <country key="FR">France</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Bertrand Thirion, Lars Kai Hansen, Sanmi Koyejo</name>
                </respStmt>
                <imprint/>
              </monogr>
              <idno type="arxiv">1511.04898</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-im">Computer Science [cs]/Medical Imaging</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The use of brain images as markers for diseases or behavioral differences is challenged by the small effects size and the ensuing lack of power, an issue that has incited researchers to rely more systematically on large cohorts. Coupled with resolution increases, this leads to very large datasets. A striking example in the case of brain imaging is that of the Human Connectome Project: 20 Terabytes of data and growing. The resulting data deluge poses severe challenges regarding the tractability of some processing steps (discriminant analysis, multivariate models) due to the memory demands posed by these data. In this work, we revisit dimension reduction approaches, such as random projections , with the aim of replacing costly function evaluations by cheaper ones while decreasing the memory requirements. Specifically, we investigate the use of alternate schemes, based on fast clustering, that are well suited for signals exhibiting a strong spatial structure, such as anatomical and functional brain images. Our contribution is twofold: i) we propose a linear-time clustering scheme that bypasses the percolation issues inherent in these algorithms and thus provides compressions nearly as good as traditional quadratic-complexity variance-minimizing clustering schemes; ii) we show that cluster-based compression can have the virtuous effect of removing high-frequency noise, actually improving subsequent estimations steps. As a consequence , the proposed approach yields very accurate models on several large-scale problems yet with impressive gains in computational efficiency , making it possible to analyze large datasets.</p>
            </abstract>
            <particDesc>
              <org type="consortium">Medilearn / braincodes</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-56051" status="OLD">
          <idno type="RNSR">200919007A</idno>
          <orgName>Modelling brain structure, function and variability based on high-field MRI data</orgName>
          <orgName type="acronym">PARIETAL</orgName>
          <date type="start">2009-07-01</date>
          <date type="end">2022-03-31</date>
          <desc>
            <address>
              <addrLine>Neurospin, CEA Saclay, Bâtiment 145, 91191 Gif-sur-Yvette Cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-40417" type="direct"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation active="#struct-487603" type="indirect"/>
            <relation name="DRF" active="#struct-300016" type="indirect"/>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-40417" status="VALID">
          <idno type="RNSR">201722552U</idno>
          <orgName>Service NEUROSPIN</orgName>
          <orgName type="acronym">NEUROSPIN</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://joliot.cea.fr/drf/joliot/recherche/neurospin</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419361" type="direct"/>
            <relation active="#struct-487603" type="direct"/>
            <relation name="DRF" active="#struct-300016" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-32" status="VALID">
          <idno type="IdRef">161603971</idno>
          <idno type="ISNI">0000000403684081</idno>
          <idno type="RNSR">199812852H</idno>
          <idno type="ROR">https://ror.org/043n4fm24</idno>
          <idno type="Wikidata">Q3214464</idno>
          <orgName>Laboratoire Paul Painlevé - UMR 8524</orgName>
          <orgName type="acronym">LPP</orgName>
          <date type="start">2004-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Sciences et technologies - U.F.R. de Mathématiques - 59655 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://math.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR8524" active="#struct-374570" type="direct"/>
            <relation name="UMR8524" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-487603" status="VALID">
          <idno type="IdRef">262253712</idno>
          <idno type="RNSR">201722498K</idno>
          <idno type="ROR">https://ror.org/016pnwd02</idno>
          <idno type="Wikidata">Q61933008</idno>
          <orgName>Institut des Sciences du Vivant Frédéric JOLIOT</orgName>
          <orgName type="acronym">JOLIOT</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>DRFCEAGif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation name="DRF" active="#struct-300016" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300016" status="VALID">
          <idno type="IdRef">026372061</idno>
          <idno type="ISNI">0000000122998025</idno>
          <idno type="ROR">https://ror.org/00jjx8s55</idno>
          <idno type="Wikidata">Q868550</idno>
          <orgName>Commissariat à l'énergie atomique et aux énergies alternatives</orgName>
          <orgName type="acronym">CEA</orgName>
          <desc>
            <address>
              <addrLine>Centre de SaclayCentre de GrenobleCentre de Cadaracheetc</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cea.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-118511" status="VALID">
          <idno type="RNSR">200818248E</idno>
          <idno type="ROR">https://ror.org/0315e5x55</idno>
          <orgName>Centre Inria de Saclay</orgName>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'OrvesBâtiment Alan TuringCampus de l'École Polytechnique91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/saclay</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-37875" status="VALID">
          <idno type="anr">ANR-11-BINF-0004</idno>
          <idno type="program">Bio-informatique</idno>
          <orgName>NiConnect</orgName>
          <desc>Outils pour la Recherche Clinique par cartographie de la connectivité cérébrale fonctionnelle</desc>
          <date type="start">2011</date>
        </org>
        <org type="europeanProject" xml:id="projeurop-129603" status="VALID">
          <idno type="number">604102</idno>
          <idno type="program">FP7-ICT-2013-FET-F</idno>
          <idno type="call">FP7-ICT-2013-FET-F</idno>
          <orgName>HBP</orgName>
          <desc>The Human Brain Project</desc>
          <date type="start">2013-01-10</date>
          <date type="end">2017-02-28</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>