<?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-03930140</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="2026-05-24T13:27:10+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Meta-learning of Black-box Solvers Using Deep Reinforcement Learning</title>
            <author role="aut">
              <persName>
                <forename type="first">Sofian</forename>
                <surname>Chaybouti</surname>
              </persName>
              <idno type="halauthorid">2689154-0</idno>
              <affiliation ref="#struct-569607"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ludovic</forename>
                <surname>dos Santos</surname>
              </persName>
              <email type="md5">795bd2456d76301b2840fba550c9cdde</email>
              <email type="domain">lip6.fr</email>
              <idno type="idhal" notation="numeric">1243057</idno>
              <idno type="halauthorid" notation="string">1051183-1243057</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=TNPp0cwAAAAJ</idno>
              <idno type="ORCID">https://orcid.org/0009-0007-4024-8763</idno>
              <idno type="IDREF">https://www.idref.fr/226846482</idno>
              <idno type="VIAF">https://viaf.org/viaf/101152864097404820155</idno>
              <affiliation ref="#struct-1001229"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cedric</forename>
                <surname>Malherbe</surname>
              </persName>
              <idno type="halauthorid">2084104-0</idno>
              <affiliation ref="#struct-569607"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Aladin</forename>
                <surname>Virmaux</surname>
              </persName>
              <email type="md5">d1f10036e7f7f0c3bf0eb38fdec9abb6</email>
              <email type="domain">lri.fr</email>
              <idno type="idhal" notation="numeric">964967</idno>
              <idno type="halauthorid" notation="string">898345-964967</idno>
              <affiliation ref="#struct-569607"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Ludovic</forename>
                <surname>DOS SANTOS</surname>
              </persName>
              <email type="md5">b0bd077e9fca8d6144438535189d9941</email>
              <email type="domain">hotmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-01-09 10:50:34</date>
              <date type="whenModified">2023-12-05 11:01:57</date>
              <date type="whenReleased">2023-02-13 08:44:52</date>
              <date type="whenProduced">2022-12-02</date>
              <date type="whenEndEmbargoed">2023-01-09</date>
              <ref type="file" target="https://hal.science/hal-03930140v1/document">
                <date notBefore="2023-01-09"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03930140v1/file/19_meta_learning_of_black_box_sol.pdf" id="file-3930140-3434679">
                <date notBefore="2023-01-09"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1370912">
                <persName>
                  <forename>Ludovic</forename>
                  <surname>DOS SANTOS</surname>
                </persName>
                <email type="md5">b0bd077e9fca8d6144438535189d9941</email>
                <email type="domain">hotmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03930140</idno>
            <idno type="halUri">https://hal.science/hal-03930140</idno>
            <idno type="halBibtex">chaybouti:hal-03930140</idno>
            <idno type="halRefHtml">&lt;i&gt;NeurIPS 2022, MetaLearn Workshop&lt;/i&gt;, Dec 2022, New Orleans, United States</idno>
            <idno type="halRef">NeurIPS 2022, MetaLearn Workshop, Dec 2022, New Orleans, United States</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3930140-3434679"/></licence>
            </availability>
          </publicationStmt>
          <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">Meta-learning of Black-box Solvers Using Deep Reinforcement Learning</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Sofian</forename>
                    <surname>Chaybouti</surname>
                  </persName>
                  <idno type="halauthorid">2689154-0</idno>
                  <affiliation ref="#struct-569607"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ludovic</forename>
                    <surname>dos Santos</surname>
                  </persName>
                  <email type="md5">795bd2456d76301b2840fba550c9cdde</email>
                  <email type="domain">lip6.fr</email>
                  <idno type="idhal" notation="numeric">1243057</idno>
                  <idno type="halauthorid" notation="string">1051183-1243057</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=TNPp0cwAAAAJ</idno>
                  <idno type="ORCID">https://orcid.org/0009-0007-4024-8763</idno>
                  <idno type="IDREF">https://www.idref.fr/226846482</idno>
                  <idno type="VIAF">https://viaf.org/viaf/101152864097404820155</idno>
                  <affiliation ref="#struct-1001229"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cedric</forename>
                    <surname>Malherbe</surname>
                  </persName>
                  <idno type="halauthorid">2084104-0</idno>
                  <affiliation ref="#struct-569607"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Aladin</forename>
                    <surname>Virmaux</surname>
                  </persName>
                  <email type="md5">d1f10036e7f7f0c3bf0eb38fdec9abb6</email>
                  <email type="domain">lri.fr</email>
                  <idno type="idhal" notation="numeric">964967</idno>
                  <idno type="halauthorid" notation="string">898345-964967</idno>
                  <affiliation ref="#struct-569607"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>NeurIPS 2022, MetaLearn Workshop</title>
                  <date type="start">2022-12-02</date>
                  <settlement>New Orleans</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <date type="datePub">2022-12-02</date>
                </imprint>
              </monogr>
              <ref type="publisher">https://meta-learn.github.io/2022/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">optimization</term>
                <term xml:lang="en">Black-box</term>
                <term xml:lang="en">Reinforcement Learning</term>
                <term xml:lang="en">Meta-learning</term>
              </keywords>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <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>Black-box optimization does not require any specification on the function we are looking to optimize. As such, it represents one of the most general problems in optimization, and is central in many scientific areas. However in many practical cases, one must solve a sequence of black-box problems from functions originating from a specific class and hence sharing similar patterns. Classical algorithms such as evolutionary or random methods would treat each problem independently and would be oblivious of the general underlying structure. In this paper, we introduce MELBA, an algorithm that exploits the similarities among a given class of functions to learn a task-specific solver that is tailored to efficiently optimize every function from this task. More precisely, given a class of functions, the proposed algorithm learns a Transformer-based Reinforcement Learning (RL) black-box solver. First, the Transformer embeds a previously gathered set of evaluation points and their image through the function into a latent state that characterizes the current stage of the optimization process. Then, the next evaluation point is sampled according to the latent state. The black-box solver is trained using PPO and the global regret on a training set. We show experimentally the effectiveness of our solvers on various synthetic and real-life tasks including the hyperparameter optimization of ML models (SVM, XGBoost) and demonstrate that our approach is competitive with existing methods.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-569607" status="VALID">
          <orgName>Huawei Technologies France</orgName>
          <date type="start">2014-04-01</date>
          <desc>
            <address>
              <addrLine>790 avenue Dr Maurice DonatMarco Polo A06250 Mougins</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.huawei.com/fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-431513" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1001229" status="VALID">
          <orgName>Criteo AI Lab</orgName>
          <desc>
            <address>
              <addrLine>Paris</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-458139" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-431513" status="VALID">
          <idno type="ROR">https://ror.org/02rbzf697</idno>
          <orgName>Huawei Technologies France [Boulogne-Billancourt]</orgName>
          <desc>
            <address>
              <addrLine>Arcs de Seine18 quai du Point du JourCS 7000392100 Boulogne Billancourt</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-458139" status="VALID">
          <orgName>Criteo [Paris]</orgName>
          <desc>
            <address>
              <addrLine>32 rue Blanche 75 009 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.criteo.com/fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>