<?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-02883907</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="2026-05-22T06:23:11+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Forced-exploration free Strategies for Unimodal Bandits</title>
            <author role="aut">
              <persName>
                <forename type="first">Hassan</forename>
                <surname>Saber</surname>
              </persName>
              <email type="md5">a00bd5b1f11cb76ccb6c57e730288e9f</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">1074055</idno>
              <idno type="halauthorid" notation="string">1992930-1074055</idno>
              <affiliation ref="#struct-432036"/>
              <affiliation ref="#struct-1042631"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pierre</forename>
                <surname>Ménard</surname>
              </persName>
              <email type="md5">4440c2deed8441224386b1a13aba962b</email>
              <email type="domain">math.univ-toulouse.fr</email>
              <idno type="idhal" notation="numeric">1022182</idno>
              <idno type="halauthorid" notation="string">1258258-1022182</idno>
              <affiliation ref="#struct-432036"/>
              <affiliation ref="#struct-1042631"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Odalric-Ambrym</forename>
                <surname>Maillard</surname>
              </persName>
              <email type="md5">2e4c2e554a9ead49425e540bd93d475b</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">odalric-ambrym-maillard</idno>
              <idno type="idhal" notation="numeric">5563</idno>
              <idno type="halauthorid" notation="string">16038-5563</idno>
              <idno type="IDREF">https://www.idref.fr/158055594</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7935-7026</idno>
              <affiliation ref="#struct-432036"/>
              <affiliation ref="#struct-1042631"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Hassan</forename>
                <surname>SABER</surname>
              </persName>
              <email type="md5">5e100a402e571349b142a4b00de46a6e</email>
              <email type="domain">hotmail.fr</email>
            </editor>
            <funder ref="#projanr-42232"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-06-29 15:15:19</date>
              <date type="whenModified">2026-05-06 09:34:02</date>
              <date type="whenReleased">2020-06-30 09:06:47</date>
              <date type="whenProduced">2020-06-29</date>
              <date type="whenEndEmbargoed">2020-06-29</date>
              <ref type="file" target="https://hal.science/hal-02883907v1/document">
                <date notBefore="2020-06-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02883907v1/file/Forced-exploration%20free%20Strategies%20for%20Unimodal%20Bandits.pdf" id="file-2883907-2536714">
                <date notBefore="2020-06-29"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2006.16569"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="901307">
                <persName>
                  <forename>Hassan</forename>
                  <surname>SABER</surname>
                </persName>
                <email type="md5">5e100a402e571349b142a4b00de46a6e</email>
                <email type="domain">hotmail.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02883907</idno>
            <idno type="halUri">https://hal.science/hal-02883907</idno>
            <idno type="halBibtex">saber:hal-02883907</idno>
            <idno type="halRefHtml">2020</idno>
            <idno type="halRef">2020</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2883907-2536714"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <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-LILLE">INRIA Lille - Nord Europe</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="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="CRISTAL-SEQUEL" corresp="CRISTAL">CRISTAL-SEQUEL</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="CRISTAL-SCOOL" corresp="CRISTAL">SCOOL</idno>
            <idno type="stamp" n="ANR">ANR</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Forced-exploration free Strategies for Unimodal Bandits</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Hassan</forename>
                    <surname>Saber</surname>
                  </persName>
                  <email type="md5">a00bd5b1f11cb76ccb6c57e730288e9f</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">1074055</idno>
                  <idno type="halauthorid" notation="string">1992930-1074055</idno>
                  <affiliation ref="#struct-432036"/>
                  <affiliation ref="#struct-1042631"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre</forename>
                    <surname>Ménard</surname>
                  </persName>
                  <email type="md5">4440c2deed8441224386b1a13aba962b</email>
                  <email type="domain">math.univ-toulouse.fr</email>
                  <idno type="idhal" notation="numeric">1022182</idno>
                  <idno type="halauthorid" notation="string">1258258-1022182</idno>
                  <affiliation ref="#struct-432036"/>
                  <affiliation ref="#struct-1042631"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Odalric-Ambrym</forename>
                    <surname>Maillard</surname>
                  </persName>
                  <email type="md5">2e4c2e554a9ead49425e540bd93d475b</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">odalric-ambrym-maillard</idno>
                  <idno type="idhal" notation="numeric">5563</idno>
                  <idno type="halauthorid" notation="string">16038-5563</idno>
                  <idno type="IDREF">https://www.idref.fr/158055594</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7935-7026</idno>
                  <affiliation ref="#struct-432036"/>
                  <affiliation ref="#struct-1042631"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
              <idno type="arxiv">2006.16569</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Structured Bandits</term>
                <term xml:lang="en">Indexed Minimum Empirical Divergence</term>
                <term xml:lang="en">Optimal Strategy</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-it">Computer Science [cs]/Information Theory [cs.IT]</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>We consider a multi-armed bandit problem specified by a set of Gaussian or Bernoulli distributions endowed with a unimodal structure. Although this problem has been addressed in the literature (Combes and Proutiere, 2014), the state-of-the-art algorithms for such structure make appear a forced-exploration mechanism. We introduce IMED-UB, the first forced-exploration free strategy that exploits the unimodal-structure, by adapting to this setting the Indexed Minimum Empirical Divergence (IMED) strategy introduced by Honda and Takemura (2015). This strategy is proven optimal. We then derive KLUCB-UB, a KLUCB version of IMED-UB, which is also proven optimal. Owing to our proof technique, we are further able to provide a concise finite-time analysis of both strategies in an unified way. Numerical experiments show that both IMED-UB and KLUCB-UB perform similarly in practice and outperform the state-of-the-art algorithms.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-432036" status="OLD">
          <idno type="RNSR">200718281V</idno>
          <orgName>Sequential Learning</orgName>
          <orgName type="acronym">SEQUEL</orgName>
          <date type="start">2015-01-01</date>
          <date type="end">2020-10-31</date>
          <desc>
            <address>
              <addrLine>Centre Inria de l'Université de Lille ,170 Av. de Bretagne, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/sequel</ref>
          </desc>
          <listRelation>
            <relation active="#struct-104752" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-410272" type="direct"/>
            <relation name="UMR9189" active="#struct-120930" type="indirect"/>
            <relation name="UMR9189" active="#struct-374570" type="indirect"/>
            <relation name="UMR9189" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1042631" status="VALID">
          <idno type="RNSR">202023603Y</idno>
          <idno type="ROR">https://ror.org/025wa0q37</idno>
          <orgName>Prise de décision séquentielle dans l’incertain</orgName>
          <orgName type="acronym">Scool</orgName>
          <date type="start">2020-07-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <addrLine>Sequential decision making under uncertainty problemParc Scientifique de la Haute Borne 40, avenue Halley Bât.A, Park Plaza 59650 Villeneuve d'Ascq</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-104752" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-410272" type="direct"/>
            <relation name="UMR9189" active="#struct-120930" type="indirect"/>
            <relation name="UMR9189" active="#struct-374570" type="indirect"/>
            <relation name="UMR9189" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-104752" status="VALID">
          <idno type="RNSR">200818245B</idno>
          <idno type="ROR">https://ror.org/04eej9726</idno>
          <orgName>Centre Inria de l'Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>Parc Scientifique de la Haute Borne 40, avenue Halley Bât.A, Park Plaza 59650 Villeneuve d'Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/lille/</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="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</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-42232" status="VALID">
          <idno type="anr">ANR-16-CE40-0002</idno>
          <orgName>BADASS</orgName>
          <desc>BANDITS MANCHOTS POUR SIGNAUX NON-STATIONNAIRES ET STRUCTURES</desc>
          <date type="start">2016</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>