<?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 inria-00000549</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="2026-04-24T09:27:20+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Statistical Learning Theory Approach of Bloat</title>
            <author role="aut">
              <persName>
                <forename type="first">Olivier</forename>
                <surname>Teytaud</surname>
              </persName>
              <email type="md5">f85d7d9588dc9f40fae54e7cc20b5e3d</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">olivier-teytaud</idno>
              <idno type="idhal" notation="numeric">581</idno>
              <idno type="halauthorid" notation="string">3437-581</idno>
              <idno type="IDREF">https://www.idref.fr/05971008X</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5570-5209</idno>
              <affiliation ref="#struct-56057"/>
              <affiliation ref="#struct-2495"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sylvain</forename>
                <surname>Gelly</surname>
              </persName>
              <idno type="halauthorid">111451-0</idno>
              <affiliation ref="#struct-56057"/>
              <affiliation ref="#struct-2495"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Bredeche</surname>
              </persName>
              <email type="md5">cf00c6846a32ba8629f9b1855ea17eff</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="string">nicolas-bredeche</idno>
              <idno type="idhal" notation="numeric">184446</idno>
              <idno type="halauthorid" notation="string">773-184446</idno>
              <idno type="ARXIV">https://arxiv.org/a/bredeche_n_1</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8241-7461</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=E7faEY8AAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/070019452</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9100-1855</idno>
              <idno type="ISNI">http://isni.org/isni/0000000140207485</idno>
              <idno type="VIAF">https://viaf.org/viaf/214135117</idno>
              <affiliation ref="#struct-56057"/>
              <affiliation ref="#struct-2495"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marc</forename>
                <surname>Schoenauer</surname>
              </persName>
              <email type="md5">6d215912b3c086d74cc5d8f7f3824951</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">evomarc</idno>
              <idno type="idhal" notation="numeric">739309</idno>
              <idno type="halauthorid" notation="string">3534-739309</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1450-6830</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=GrCk6WoAAAAJ&amp;hl=en</idno>
              <idno type="IDREF">https://www.idref.fr/057775575</idno>
              <affiliation ref="#struct-56057"/>
              <affiliation ref="#struct-2495"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sylvain</forename>
                <surname>Gelly</surname>
              </persName>
              <email type="md5">8152fbd21094b0d2df3cf0f25da842e2</email>
              <email type="domain">m4x.org</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2005-11-02 11:05:13</date>
              <date type="whenModified">2025-07-10 03:08:44</date>
              <date type="whenReleased">2005-11-02 11:08:44</date>
              <date type="whenProduced">2005-06-25</date>
              <date type="whenEndEmbargoed">2005-11-02</date>
              <ref type="file" target="https://inria.hal.science/inria-00000549v1/document">
                <date notBefore="2005-11-02"/>
              </ref>
              <ref type="file" n="1" target="https://inria.hal.science/inria-00000549v1/file/antibloatGecco2005_long_version.pdf" id="file-41972-178923">
                <date notBefore="2005-11-02"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="103732">
                <persName>
                  <forename>Sylvain</forename>
                  <surname>Gelly</surname>
                </persName>
                <email type="md5">8152fbd21094b0d2df3cf0f25da842e2</email>
                <email type="domain">m4x.org</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">inria-00000549</idno>
            <idno type="halUri">https://inria.hal.science/inria-00000549</idno>
            <idno type="halBibtex">teytaud:inria-00000549</idno>
            <idno type="halRefHtml">&lt;i&gt;Genetic and Evolutionary Computation Conference&lt;/i&gt;, Jun 2005, Washington D.C., United States</idno>
            <idno type="halRef">Genetic and Evolutionary Computation Conference, Jun 2005, Washington D.C., United States</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-41972-178923"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="X">École polytechnique</idno>
            <idno type="stamp" n="EC-PARIS">Ecole Centrale Paris</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="UNIV-PSUD">Université Paris Sud - Paris XI</idno>
            <idno type="stamp" n="INRIA-FUTURS">Inria Futurs</idno>
            <idno type="stamp" n="INRIA-SACLAY" corresp="INRIA">INRIA Saclay - Ile de France</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</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="UMR8623">Laboratoire de Recherche en Informatique</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LRI-AO" corresp="UMR8623">Laboratoire de recherche en informatique. Équipe: Apprentissage et optimisation</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PSUD-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris Sud pour Paris Saclay</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="1">Not set</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A Statistical Learning Theory Approach of Bloat</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Olivier</forename>
                    <surname>Teytaud</surname>
                  </persName>
                  <email type="md5">f85d7d9588dc9f40fae54e7cc20b5e3d</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">olivier-teytaud</idno>
                  <idno type="idhal" notation="numeric">581</idno>
                  <idno type="halauthorid" notation="string">3437-581</idno>
                  <idno type="IDREF">https://www.idref.fr/05971008X</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5570-5209</idno>
                  <affiliation ref="#struct-56057"/>
                  <affiliation ref="#struct-2495"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sylvain</forename>
                    <surname>Gelly</surname>
                  </persName>
                  <idno type="halauthorid">111451-0</idno>
                  <affiliation ref="#struct-56057"/>
                  <affiliation ref="#struct-2495"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Bredeche</surname>
                  </persName>
                  <email type="md5">cf00c6846a32ba8629f9b1855ea17eff</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="string">nicolas-bredeche</idno>
                  <idno type="idhal" notation="numeric">184446</idno>
                  <idno type="halauthorid" notation="string">773-184446</idno>
                  <idno type="ARXIV">https://arxiv.org/a/bredeche_n_1</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8241-7461</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=E7faEY8AAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/070019452</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9100-1855</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000140207485</idno>
                  <idno type="VIAF">https://viaf.org/viaf/214135117</idno>
                  <affiliation ref="#struct-56057"/>
                  <affiliation ref="#struct-2495"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc</forename>
                    <surname>Schoenauer</surname>
                  </persName>
                  <email type="md5">6d215912b3c086d74cc5d8f7f3824951</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">evomarc</idno>
                  <idno type="idhal" notation="numeric">739309</idno>
                  <idno type="halauthorid" notation="string">3534-739309</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1450-6830</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=GrCk6WoAAAAJ&amp;hl=en</idno>
                  <idno type="IDREF">https://www.idref.fr/057775575</idno>
                  <affiliation ref="#struct-56057"/>
                  <affiliation ref="#struct-2495"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Genetic and Evolutionary Computation Conference</title>
                  <date type="start">2005-06-25</date>
                  <settlement>Washington D.C.</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Genetic and Evolutionary Computation Conference 2005 (p427-428)</biblScope>
                  <date type="datePub">2005-06-25</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</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>Code bloat, the excessive increase of code size, is an important is- sue in Genetic Programming (GP). This paper proposes a theoreti- cal analysis of code bloat in the framework of symbolic regression in GP, from the viewpoint of Statistical Learning Theory, a well grounded mathematical toolbox for Machine Learning. Two kinds of bloat must be distinguished in that context, depending whether the target function lies in the search space or not. Then, important mathematical results are proved using classical results from Sta- tistical Learning. Namely, the Vapnik-Cervonenkis dimension of programs is computed, and further results from Statistical Learn- ing allow to prove that a parsimonious fitness ensures Universal Consistency (the solution minimizing the empirical error does con- verge to the best possible error when the number of samples goes to infinity). However, it is proved that the standard method consisting in choosing a maximal program size depending on the number of samples might still result in programs of infinitely increasing size whith their accuracy; a more complicated modification of the fit- ness is proposed that theoretically avoids unnecessary bloat while nevertheless preserving the Universal Consistency.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-56057" status="OLD">
          <idno type="RNSR">200418366A</idno>
          <orgName>Machine Learning and Optimisation</orgName>
          <orgName type="acronym">TAO</orgName>
          <date type="start">2004-11-04</date>
          <date type="end">2016-12-31</date>
          <desc>
            <address>
              <addrLine>DIGITEO Bat. Claude Shannon - Université de Paris-Sud, Bâtiment 660, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/tao</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2544" type="direct"/>
            <relation active="#struct-92966" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR8623" active="#struct-441569" type="indirect"/>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2495" status="OLD">
          <orgName>INRIA Futurs</orgName>
          <desc>
            <address>
              <addrLine>Parc Club Orsay Université ZAC des vignes 4 rue Jacques Monod - Bât G 91893 Orsay CedexTél. : (+33) 1 72 92 59 00</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www-futurs.inria.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2544" status="OLD">
          <idno type="RNSR">199812948M</idno>
          <orgName>Laboratoire de Recherche en Informatique</orgName>
          <orgName type="acronym">LRI</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>LRI - Bâtiments 650-660 Université Paris-Sud 91405 Orsay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lri.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation name="UMR8623" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-92966" status="OLD">
          <idno type="ROR">https://ror.org/028rypz17</idno>
          <orgName>Université Paris-Sud - Paris 11</orgName>
          <orgName type="acronym">UP11</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 300 - 91405 Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-psud.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.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>
        <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>
      </listOrg>
    </back>
  </text>
</TEI>