<?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-03339123</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="2026-05-24T20:53:29+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits</title>
            <author role="aut">
              <persName>
                <forename type="first">Marc</forename>
                <surname>Abeille</surname>
              </persName>
              <idno type="halauthorid">1151364-0</idno>
              <affiliation ref="#struct-1001229"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Louis</forename>
                <surname>Faury</surname>
              </persName>
              <idno type="halauthorid">1516247-0</idno>
              <affiliation ref="#struct-1001229"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Clément</forename>
                <surname>Calauzènes</surname>
              </persName>
              <idno type="halauthorid">18344-0</idno>
              <affiliation ref="#struct-1001229"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Louis</forename>
                <surname>Faury</surname>
              </persName>
              <email type="md5">25d7871707b9f5a80bf02e025036e086</email>
              <email type="domain">criteo.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-09-09 12:20:12</date>
              <date type="whenModified">2024-04-22 16:53:00</date>
              <date type="whenReleased">2021-09-09 12:20:12</date>
              <date type="whenProduced">2021-04-13</date>
              <ref type="externalLink" target="http://arxiv.org/pdf/2010.12642"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="846875">
                <persName>
                  <forename>Louis</forename>
                  <surname>Faury</surname>
                </persName>
                <email type="md5">25d7871707b9f5a80bf02e025036e086</email>
                <email type="domain">criteo.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03339123</idno>
            <idno type="halUri">https://hal.science/hal-03339123</idno>
            <idno type="halBibtex">abeille:hal-03339123</idno>
            <idno type="halRefHtml">&lt;i&gt;AISTATS&lt;/i&gt;, Apr 2021, Virtual Conference, France</idno>
            <idno type="halRef">AISTATS, Apr 2021, Virtual Conference, France</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt>
            <note type="commentary">40 pages. AISTATS 2021, oral</note>
            <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">Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc</forename>
                    <surname>Abeille</surname>
                  </persName>
                  <idno type="halauthorid">1151364-0</idno>
                  <affiliation ref="#struct-1001229"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Louis</forename>
                    <surname>Faury</surname>
                  </persName>
                  <idno type="halauthorid">1516247-0</idno>
                  <affiliation ref="#struct-1001229"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Clément</forename>
                    <surname>Calauzènes</surname>
                  </persName>
                  <idno type="halauthorid">18344-0</idno>
                  <affiliation ref="#struct-1001229"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>AISTATS</title>
                  <date type="start">2021-04-13</date>
                  <settlement>Virtual Conference</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
              <idno type="arxiv">2010.12642</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <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>Logistic Bandits have recently attracted substantial attention, by providing an uncluttered yet challenging framework for understanding the impact of non-linearity in parametrized bandits. It was shown by Faury et al. (2020) that the learning-theoretic difficulties of Logistic Bandits can be embodied by a large (sometimes prohibitively) problem-dependent constant $\kappa$, characterizing the magnitude of the reward's non-linearity. In this paper we introduce a novel algorithm for which we provide a refined analysis. This allows for a better characterization of the effect of non-linearity and yields improved problem-dependent guarantees. In most favorable cases this leads to a regret upper-bound scaling as $\tilde{\mathcal{O}}(d\sqrt{T/\kappa})$, which dramatically improves over the $\tilde{\mathcal{O}}(d\sqrt{T}+\kappa)$ state-of-the-art guarantees. We prove that this rate is minimax-optimal by deriving a $\Omega(d\sqrt{T/\kappa})$ problem-dependent lower-bound. Our analysis identifies two regimes (permanent and transitory) of the regret, which ultimately re-conciliates Faury et al. (2020) with the Bayesian approach of Dong et al. (2019). In contrast to previous works, we find that in the permanent regime non-linearity can dramatically ease the exploration-exploitation trade-off. While it also impacts the length of the transitory phase in a problem-dependent fashion, we show that this impact is mild in most reasonable configurations.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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-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>