{"id":"https://openalex.org/W2883844088","doi":null,"title":"An Optimal Algorithm for Stochastic and Adversarial Bandits","display_name":"An Optimal Algorithm for Stochastic and Adversarial Bandits","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2883844088","mag":"2883844088"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/691f32db-1f27-4f3b-8dd7-df37b3635cdd","doi":null,"is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/691f32db-1f27-4f3b-8dd7-df37b3635cdd","pdf_url":"http://proceedings.mlr.press/v89/zimmert19a/zimmert19a-supp.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zimmert , J U & Seldin , Y 2019 , An Optimal Algorithm for Stochastic and Adversarial Bandits . in K Chaudhuri & M Sugiyama (eds) , Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) . PMLR , Proceedings of Machine Learning Research , vol. 89 , pp. 467-475 , 22nd International Conference on Artificial Intelligence and Statistics (AISTAT) , Naha, Okinawa , Japan , 16/04/2019 . < http://proceedings.mlr.press/v89/zimmert19a/zimmert19a-supp.pdf >","raw_type":"contributionToPeriodical"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://proceedings.mlr.press/v89/zimmert19a/zimmert19a-supp.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022323474","display_name":"Julian Zimmert","orcid":"https://orcid.org/0000-0001-6929-9053","observed_orcids":["https://orcid.org/0000-0001-6929-9053"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Julian Zimmert","raw_affiliation_strings":["University of Copenhagen","K\u00f8benhavns Universitet, Faculty of Science, Department of Computer Science, Machine Learning, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"K\u00f8benhavns Universitet, Faculty of Science, Department of Computer Science, Machine Learning, DK","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021828946","display_name":"Yevgeny Seldin","orcid":"https://orcid.org/0000-0003-3152-4635","observed_orcids":["https://orcid.org/0000-0003-3152-4635"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Yevgeny Seldin","raw_affiliation_strings":["University of Copenhagen","K\u00f8benhavns Universitet, Faculty of Science, Department of Computer Science, Machine Learning, DK"],"raw_orcid":"https://orcid.org/0000-0003-3152-4635","affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"K\u00f8benhavns Universitet, Faculty of Science, Department of Computer Science, Machine Learning, DK","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":26.5248,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.99818794,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"467","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.9789999723434448},{"id":"https://openalex.org/keywords/adversarial-bandits","display_name":"adversarial bandits","score":0.847000002861023},{"id":"https://openalex.org/keywords/stochastic-multi-armed-bandits","display_name":"stochastic bandits","score":0.9850000143051147},{"id":"https://openalex.org/keywords/online-mirror-descent","display_name":"online mirror descent","score":0.8519999980926514},{"id":"https://openalex.org/keywords/tsallis-entropy","display_name":"Tsallis entropy","score":0.8889999985694885},{"id":"https://openalex.org/keywords/regret-minimization","display_name":"regret minimization","score":0.5460000038146973},{"id":"https://openalex.org/keywords/dueling-bandits","display_name":"dueling bandits","score":0.8999999761581421},{"id":"https://openalex.org/keywords/ucb1","display_name":"UCB1","score":0.6819999814033508},{"id":"https://openalex.org/keywords/exp3","display_name":"EXP3","score":0.8709999918937683},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.949999988079071}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.855853259563446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5962885022163391},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5068259835243225},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4250539541244507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3489236831665039},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2517707347869873}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/691f32db-1f27-4f3b-8dd7-df37b3635cdd","doi":null,"is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/691f32db-1f27-4f3b-8dd7-df37b3635cdd","pdf_url":"http://proceedings.mlr.press/v89/zimmert19a/zimmert19a-supp.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zimmert , J U & Seldin , Y 2019 , An Optimal Algorithm for Stochastic and Adversarial Bandits . in K Chaudhuri & M Sugiyama (eds) , Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) . PMLR , Proceedings of Machine Learning Research , vol. 89 , pp. 467-475 , 22nd International Conference on Artificial Intelligence and Statistics (AISTAT) , Naha, Okinawa , Japan , 16/04/2019 . < http://proceedings.mlr.press/v89/zimmert19a/zimmert19a-supp.pdf >","raw_type":"contributionToPeriodical"},{"id":"mag:2883844088","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1807.07623v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"mag:2964332112","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v89/zimmert19a/zimmert19a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419146","display_name":"International Conference on Artificial Intelligence and Statistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Artificial Intelligence and Statistics","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/691f32db-1f27-4f3b-8dd7-df37b3635cdd","doi":null,"is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/691f32db-1f27-4f3b-8dd7-df37b3635cdd","pdf_url":"http://proceedings.mlr.press/v89/zimmert19a/zimmert19a-supp.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zimmert , J U & Seldin , Y 2019 , An Optimal Algorithm for Stochastic and Adversarial Bandits . in K Chaudhuri & M Sugiyama (eds) , Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) . PMLR , Proceedings of Machine Learning Research , vol. 89 , pp. 467-475 , 22nd International Conference on Artificial Intelligence and Statistics (AISTAT) , Naha, Okinawa , Japan , 16/04/2019 . < http://proceedings.mlr.press/v89/zimmert19a/zimmert19a-supp.pdf >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2883844088.pdf","grobid_xml":"https://content.openalex.org/works/W2883844088.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2792619169"],"related_works":["https://openalex.org/W2972784128","https://openalex.org/W2402892507","https://openalex.org/W7098264679","https://openalex.org/W165458731","https://openalex.org/W3046884627","https://openalex.org/W2225232604","https://openalex.org/W2911959363","https://openalex.org/W7096868863","https://openalex.org/W3173818868","https://openalex.org/W3133152052"],"abstract_inverted_index":{"We":[0,40,108],"derive":[1],"an":[2],"algorithm":[3,29,63,95,114,130],"that":[4,50,116],"achieves":[5,56,97],"the":[6,23,57,61,72,84,103,113,129],"optimal":[7],"(up":[8],"to":[9],"constants)":[10],"pseudo-regret":[11],"in":[12,68,102,122],"both":[13],"adversarial":[14,98,127],"and":[15,25,48,80,83,91,99,120,134],"stochastic":[16,75,100,123],"multi-armed":[17],"bandits":[18],"without":[19],"prior":[20],"knowledge":[21],"of":[22,45,112],"regime":[24,76],"time":[26],"horizon.":[27],"The":[28,94],"is":[30],"based":[31],"on":[32],"online":[33],"mirror":[34],"descent":[35],"with":[36,53],"Tsallis":[37,51],"entropy":[38,52],"regularizer.":[39],"provide":[41,109],"a":[42],"complete":[43],"characterization":[44],"such":[46],"algorithms":[47],"show":[49],"power":[54],"\u03b1=1/2":[55],"goal.":[58],"In":[59,125],"addition,":[60],"proposed":[62],"enjoys":[64],"improved":[65],"regret":[66],"guarantees":[67],"two":[69],"intermediate":[70],"regimes:":[71],"moderately":[73],"contaminated":[74],"defined":[77],"by":[78,89],"Seldin":[79],"Slivkins":[81],"(2014)":[82],"stochastically":[85],"constrained":[86],"adversary":[87],"studied":[88],"Wei":[90],"Luo":[92],"(2018).":[93],"also":[96],"optimality":[101],"utility-based":[104],"dueling":[105],"bandit":[106],"setting.":[107],"empirical":[110],"evaluation":[111],"demonstrating":[115],"it":[117],"outperforms":[118,132],"UCB1":[119,133],"EXP3":[121],"environments.":[124],"certain":[126],"regimes":[128],"significantly":[131],"Thompson":[135],"Sampling,":[136],"which":[137],"exhibit":[138],"almost":[139],"linear":[140],"regret.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":55},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-08-03T00:00:00"}