<?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-04370990</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="2026-05-02T09:12:35+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">MG-CNN: A Deep CNN To Predict Saddle Points Of Matrix Games</title>
            <author role="aut">
              <persName>
                <forename type="first">Dawen</forename>
                <surname>Wu</surname>
              </persName>
              <email type="md5">c0bf994810f419cf0003dd55e1112905</email>
              <email type="domain">cnrsatcreate.sg</email>
              <idno type="idhal" notation="numeric">1331220</idno>
              <idno type="halauthorid" notation="string">2282365-1331220</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6450-9365</idno>
              <affiliation ref="#struct-1051117"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Abdel</forename>
                <surname>Lisser</surname>
              </persName>
              <email type="md5">f9048af9dc25411e07ac0b6eb88e7b49</email>
              <email type="domain">l2s.centralesupelec.fr</email>
              <idno type="idhal" notation="string">abdel-lisser</idno>
              <idno type="idhal" notation="numeric">11208</idno>
              <idno type="halauthorid" notation="string">20724-11208</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1318-6679</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=X05CPd0AAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/032881983</idno>
              <affiliation ref="#struct-1051117"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Dawen</forename>
                <surname>Wu</surname>
              </persName>
              <email type="md5">d9adab90837143140b6007610e84d552</email>
              <email type="domain">centralesupelec.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-01-03 14:51:25</date>
              <date type="whenModified">2025-02-20 18:02:35</date>
              <date type="whenReleased">2024-01-04 16:08:33</date>
              <date type="whenProduced">2022-12-01</date>
              <date type="whenEndEmbargoed">2024-01-03</date>
              <ref type="file" target="https://hal.science/hal-04370990v1/document">
                <date notBefore="2024-01-03"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04370990v1/file/No__6_Maple_leaf__manuscript__1st_revision_%20%285%29.pdf" id="file-4370990-3803560">
                <date notBefore="2024-01-03"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1069579">
                <persName>
                  <forename>Dawen</forename>
                  <surname>Wu</surname>
                </persName>
                <email type="md5">d9adab90837143140b6007610e84d552</email>
                <email type="domain">centralesupelec.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04370990</idno>
            <idno type="halUri">https://hal.science/hal-04370990</idno>
            <idno type="halBibtex">wu:hal-04370990</idno>
            <idno type="halRefHtml">&lt;i&gt;Neural Networks&lt;/i&gt;, 2022, 156, pp.49-57. &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.neunet.2022.09.014"&gt;&amp;#x27E8;10.1016/j.neunet.2022.09.014&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Neural Networks, 2022, 156, pp.49-57. &amp;#x27E8;10.1016/j.neunet.2022.09.014&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4370990-3803560"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="SUP_LSS">Laboratoire des Signaux et Systèmes</idno>
            <idno type="stamp" n="SUP_TELECOMS" corresp="SUP_LSS">Pôle Télécoms et Réseaux</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="GS-SPORT-HUMAN-MOVEMENT">Graduate School Sport, Mouvement, Facteurs Humains</idno>
            <idno type="stamp" n="HUB-IA">Hub Intelligence Artificielle de CentraleSupélec</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">MG-CNN: A Deep CNN To Predict Saddle Points Of Matrix Games</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Dawen</forename>
                    <surname>Wu</surname>
                  </persName>
                  <email type="md5">c0bf994810f419cf0003dd55e1112905</email>
                  <email type="domain">cnrsatcreate.sg</email>
                  <idno type="idhal" notation="numeric">1331220</idno>
                  <idno type="halauthorid" notation="string">2282365-1331220</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6450-9365</idno>
                  <affiliation ref="#struct-1051117"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Abdel</forename>
                    <surname>Lisser</surname>
                  </persName>
                  <email type="md5">f9048af9dc25411e07ac0b6eb88e7b49</email>
                  <email type="domain">l2s.centralesupelec.fr</email>
                  <idno type="idhal" notation="string">abdel-lisser</idno>
                  <idno type="idhal" notation="numeric">11208</idno>
                  <idno type="halauthorid" notation="string">20724-11208</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1318-6679</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=X05CPd0AAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/032881983</idno>
                  <affiliation ref="#struct-1051117"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">7360</idno>
                <idno type="issn">0893-6080</idno>
                <title level="j">Neural Networks</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <biblScope unit="volume">156</biblScope>
                  <biblScope unit="pp">49-57</biblScope>
                  <date type="datePub">2022-12-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.neunet.2022.09.014</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Convolutional neural network Saddle point Matrix game</term>
                <term xml:lang="en">Convolutional neural network</term>
                <term xml:lang="en">Saddle point</term>
                <term xml:lang="en">Matrix game</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Finding the saddle point of a matrix game is a classical problem that arises in various fields, e.g., economics, computer science, and engineering. The standard problem-solving methods consist of formulating the problem as a linear program (LP). However, this approach seems to be inappropriate, especially when multiple instances need to be solved. In this paper, we propose a Convolutional Neural Network based approach, which is able to predict both the strategy profile (x, y) and the optimal value v of the game. We call this approach Matrix Game-Conventional Neural Network or MG-CNN for short. Thanks to a global pooling technique, MG-CNN can solve matrix games with different shapes. We propose a specialized algorithm to train MG-CNN, which includes both data generation and model training. Our numerical experiments show that MG-CNN outperforms standard LP solvers in terms of computational CPU time and provides a high quality prediction.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1051117" status="VALID">
          <idno type="IdRef">133818799</idno>
          <idno type="RNSR">199812842X</idno>
          <idno type="ROR">https://ror.org/00skw9v43</idno>
          <orgName>Laboratoire des signaux et systèmes</orgName>
          <orgName type="acronym">L2S</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.l2s.centralesupelec.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UMR8506" active="#struct-441569" type="direct"/>
          </listRelation>
        </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="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="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>
    </back>
  </text>
</TEI>