<?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-01615427</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="2026-05-20T01:00:43+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Boundary Crossing for General Exponential Families</title>
            <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"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Odalric-Ambrym</forename>
                <surname>Maillard</surname>
              </persName>
              <email type="md5">2e4c2e554a9ead49425e540bd93d475b</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-42232"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-10-12 13:20:28</date>
              <date type="whenModified">2025-02-26 15:33:49</date>
              <date type="whenReleased">2017-10-13 14:20:05</date>
              <date type="whenProduced">2017-10</date>
              <date type="whenEndEmbargoed">2017-10-12</date>
              <ref type="file" target="https://hal.science/hal-01615427v1/document">
                <date notBefore="2017-10-12"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01615427v1/file/15.pdf" id="file-1615427-1658888">
                <date notBefore="2017-10-12"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="151002">
                <persName>
                  <forename>Odalric-Ambrym</forename>
                  <surname>Maillard</surname>
                </persName>
                <email type="md5">2e4c2e554a9ead49425e540bd93d475b</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01615427</idno>
            <idno type="halUri">https://hal.science/hal-01615427</idno>
            <idno type="halBibtex">maillard:hal-01615427</idno>
            <idno type="halRefHtml">&lt;i&gt;Algorithmic Learning Theory&lt;/i&gt;, Oct 2017, Kyoto, Japan. pp.1 - 34</idno>
            <idno type="halRef">Algorithmic Learning Theory, Oct 2017, Kyoto, Japan. pp.1 - 34</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1615427-1658888"/></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="INRIA2017">INRIA2017</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="ANR">ANR</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Boundary Crossing for General Exponential Families</title>
                <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"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Journal of Machine Learning Research</title>
                <meeting>
                  <title>Algorithmic Learning Theory</title>
                  <date type="start">2017-10</date>
                  <settlement>Kyoto</settlement>
                  <country key="JP">Japan</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Proceedings of Algorithmic Learning Theory</biblScope>
                  <biblScope unit="volume">1</biblScope>
                  <biblScope unit="pp">1 - 34</biblScope>
                  <date type="datePub">2017</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Optimality</term>
                <term xml:lang="en">Multi-armed Bandits</term>
                <term xml:lang="en">Bregman Concentration</term>
                <term xml:lang="en">Exponential Families</term>
              </keywords>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halDomain" n="math.math-st">Mathematics [math]/Statistics [math.ST]</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>We consider parametric exponential families of dimension K on the real line. We study a variant of boundary crossing probabilities coming from the multi-armed bandit literature, in the case when the real-valued distributions form an exponential family of dimension K. Formally, our result is a concentration inequality that bounds the probability that B ψ (θ n , θ) f (t/n)/n, where θ is the parameter of an unknown target distribution, θ n is the empirical parameter estimate built from n observations, ψ is the log-partition function of the exponential family and B ψ is the corresponding Bregman divergence. From the perspective of stochastic multi-armed bandits, we pay special attention to the case when the boundary function f is logarithmic, as it enables to analyze the regret of the state-of-the-art KL-ucb and KL-ucb+ strategies, whose analysis was left open in such generality. Indeed, previous results only hold for the case when K = 1, while we provide results for arbitrary finite dimension K, thus considerably extending the existing results. Perhaps surprisingly, we highlight that the proof techniques to achieve these strong results already existed three decades ago in the work of T.L. Lai, and were apparently forgotten in the bandit community. We provide a modern rewriting of these beautiful techniques that we believe are useful beyond the application to stochastic multi-armed bandits.</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="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>