{"id":"https://openalex.org/W2962847271","doi":"https://doi.org/10.48550/arxiv.1708.01799","title":"Efficient Contextual Bandits in Non-stationary Worlds","display_name":"Efficient Contextual Bandits in Non-stationary Worlds","publication_year":2017,"publication_date":"2017-08-05","ids":{"openalex":"https://openalex.org/W2962847271","doi":"https://doi.org/10.48550/arxiv.1708.01799","mag":"2962847271"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1708.01799","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.01799","pdf_url":"https://arxiv.org/pdf/1708.01799","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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1708.01799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101058302","display_name":"Haipeng Luo","orcid":"https://orcid.org/0009-0002-4142-3627","observed_orcids":["https://orcid.org/0009-0002-4142-3627"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luo, Haipeng","raw_affiliation_strings":["University of Southern California, Los Angeles, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035849375","display_name":"Chen-Yu Wei","orcid":"https://orcid.org/0000-0003-3890-8260","observed_orcids":["https://orcid.org/0000-0003-3890-8260","https://orcid.org/0000-0001-8735-4773"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei, Chen-Yu","raw_affiliation_strings":["University of Southern California, Los Angeles, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036435487","display_name":"Alekh Agarwal","orcid":"https://orcid.org/0000-0001-7032-7162","observed_orcids":["https://orcid.org/0000-0001-7032-7162"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agarwal, Alekh","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005003250","display_name":"John C. Langford","orcid":"https://orcid.org/0000-0002-9811-3550","observed_orcids":["https://orcid.org/0000-0002-9811-3550"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Langford, John","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1739","last_page":"1776"},"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/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contextual-bandits","display_name":"contextual bandits","score":0.996999979019165},{"id":"https://openalex.org/keywords/non-stationary-environments","display_name":"non-stationary environments","score":0.9860000014305115},{"id":"https://openalex.org/keywords/dynamic-regret","display_name":"dynamic regret","score":0.7919999957084656},{"id":"https://openalex.org/keywords/hypothesis-testing","display_name":"hypothesis testing","score":0.5400000214576721},{"id":"https://openalex.org/keywords/parameter-free-algorithms","display_name":"parameter-free algorithms","score":0.8349999785423279},{"id":"https://openalex.org/keywords/adversarial-bandits","display_name":"adversarial bandits","score":0.7490000128746033},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.3930000066757202},{"id":"https://openalex.org/keywords/distribution-change-detection","display_name":"distribution change detection","score":0.42800000309944153}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9767096042633057},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6647688150405884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.540199339389801},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48564329743385315},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4819495379924774},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4682173728942871},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3420391082763672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.199970543384552},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.17308297753334045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15234825015068054},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1708.01799","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.01799","pdf_url":"https://arxiv.org/pdf/1708.01799","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1708.01799","doi":"https://doi.org/10.48550/arxiv.1708.01799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.01799","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2962847271","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v75/luo18a/luo18a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418075","display_name":"Conference on Learning Theory","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":"Conference on Learning Theory","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.01799","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.01799","pdf_url":"https://arxiv.org/pdf/1708.01799","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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.5099999904632568}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2914791924","https://openalex.org/W3006045248","https://openalex.org/W2920202034","https://openalex.org/W7202161614","https://openalex.org/W2798369493","https://openalex.org/W4323557210","https://openalex.org/W4387647989","https://openalex.org/W3134572644","https://openalex.org/W4286859167","https://openalex.org/W3037657204"],"abstract_inverted_index":{"Most":[0],"contextual":[1,29,148],"bandit":[2,30,198],"algorithms":[3,31,90],"minimize":[4],"regret":[5,62,92,136,175],"against":[6],"the":[7,81,117,130,140,152,161,182,196],"best":[8,82,183],"fixed":[9],"policy,":[10],"a":[11,52,127,157,170],"questionable":[12],"benchmark":[13],"for":[14,32,39,67,143,195],"non-stationary":[15,33,65],"environments":[16,34,66],"that":[17,125],"are":[18,96],"ubiquitous":[19],"in":[20,54],"applications.":[21],"In":[22],"this":[23],"work,":[24],"we":[25,167],"develop":[26,169],"several":[27],"efficient":[28,144],"by":[35,121,187],"equipping":[36],"existing":[37,184],"methods":[38],"i.i.d.":[40],"problems":[41],"with":[42,80,99],"sophisticated":[43],"statistical":[44],"tests":[45],"so":[46],"as":[47],"to":[48,51,64],"dynamically":[49],"adapt":[50],"change":[53],"distribution.":[55],"We":[56],"analyze":[57],"various":[58],"standard":[59],"notions":[60],"of":[61,88,129],"suited":[63],"these":[68],"algorithms,":[69],"including":[70],"interval":[71],"regret,":[72,74],"switching":[73],"and":[75,145,180,189],"dynamic":[76,135],"regret.":[77],"When":[78],"competing":[79],"policy":[83],"at":[84],"each":[85],"time,":[86],"one":[87,142],"our":[89],"achieves":[91],"$\\mathcal{O}(\\sqrt{ST})$":[93],"if":[94],"there":[95],"$T$":[97],"rounds":[98],"$S$":[100,164],"stationary":[101],"periods,":[102],"or":[103,165],"more":[104],"generally":[105],"$\\mathcal{O}(\u0394^{1/3}T^{2/3})$":[106],"where":[107],"$\u0394$":[108],"is":[109,126,138],"some":[110],"non-stationarity":[111],"measure.":[112],"These":[113],"results":[114,153],"almost":[115],"match":[116],"optimal":[118],"guarantees":[119],"achieved":[120],"an":[122],"inefficient":[123],"baseline":[124],"variant":[128],"classic":[131],"Exp4":[132],"algorithm.":[133],"The":[134],"result":[137,185],"also":[139,168],"first":[141],"fully":[146],"adversarial":[147],"bandit.":[149],"Furthermore,":[150],"while":[151],"above":[154],"require":[155],"tuning":[156],"parameter":[158,171],"based":[159],"on":[160],"unknown":[162],"quantity":[163],"$\u0394$,":[166],"free":[172],"algorithm":[173],"achieving":[174],"$\\min\\{S^{1/4}T^{3/4},":[176],"\u0394^{1/5}T^{4/5}\\}$.":[177],"This":[178],"improves":[179],"generalizes":[181],"$\u0394^{0.18}T^{0.82}$":[186],"Karnin":[188],"Anava":[190],"(2016)":[191],"which":[192],"only":[193],"holds":[194],"two-armed":[197],"problem.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":61},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-07-30T00:00:00"}