{"id":"https://openalex.org/W2951936005","doi":"https://doi.org/10.1145/3292500.3330862","title":"Scaling Multi-Armed Bandit Algorithms","display_name":"Scaling Multi-Armed Bandit Algorithms","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2951936005","doi":"https://doi.org/10.1145/3292500.3330862","mag":"2951936005"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034787716","display_name":"Edouard Fouch\u00e9","orcid":"https://orcid.org/0000-0003-0157-7648"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Edouard Fouch\u00e9","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038978456","display_name":"Junpei Komiyama","orcid":"https://orcid.org/0000-0003-0095-6558"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junpei Komiyama","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049768806","display_name":"Klemens B\u00f6hm","orcid":"https://orcid.org/0000-0002-1706-1913"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klemens B\u00f6hm","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034787716"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":2.5748,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8987492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1449","last_page":"1459"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9983999729156494,"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/T10603","display_name":"Smart Grid Energy Management","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.7326308488845825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7275376319885254},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5869081020355225},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5591193437576294},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.5155006051063538},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5025737285614014},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.4681888818740845},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.432937890291214},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.4124499559402466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36989080905914307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3365901708602905},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3364025950431824},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.28643134236335754},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12308469414710999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1139671802520752},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.09408855438232422}],"concepts":[{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.7326308488845825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275376319885254},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5869081020355225},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5591193437576294},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.5155006051063538},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5025737285614014},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.4681888818740845},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.432937890291214},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.4124499559402466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36989080905914307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3365901708602905},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3364025950431824},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.28643134236335754},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12308469414710999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1139671802520752},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.09408855438232422},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W157259654","https://openalex.org/W172143579","https://openalex.org/W1501823362","https://openalex.org/W1515851193","https://openalex.org/W1569127318","https://openalex.org/W1761637522","https://openalex.org/W1850547517","https://openalex.org/W1979352993","https://openalex.org/W2014482607","https://openalex.org/W2038690695","https://openalex.org/W2039522160","https://openalex.org/W2049934117","https://openalex.org/W2077902449","https://openalex.org/W2092939357","https://openalex.org/W2099419573","https://openalex.org/W2112420033","https://openalex.org/W2116067849","https://openalex.org/W2121863487","https://openalex.org/W2123016239","https://openalex.org/W2125724988","https://openalex.org/W2141645258","https://openalex.org/W2143991132","https://openalex.org/W2158319693","https://openalex.org/W2168405694","https://openalex.org/W2257238407","https://openalex.org/W2466101409","https://openalex.org/W2573607665","https://openalex.org/W2742123006","https://openalex.org/W2761139119","https://openalex.org/W2802331575","https://openalex.org/W2950929549","https://openalex.org/W2952951433","https://openalex.org/W4206530644","https://openalex.org/W4247952071","https://openalex.org/W4248403059","https://openalex.org/W4255361718","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2613863488","https://openalex.org/W2331759129","https://openalex.org/W2946219535","https://openalex.org/W2952186526","https://openalex.org/W4289887588","https://openalex.org/W2358698356","https://openalex.org/W4221165587","https://openalex.org/W2806567655","https://openalex.org/W3165844356","https://openalex.org/W2951936005"],"abstract_inverted_index":{"The":[0,58],"Multi-Armed":[1],"Bandit":[2],"(MAB)":[3],"is":[4,64,106,134],"a":[5,27,33,46,159,176],"fundamental":[6],"model":[7],"capturing":[8],"the":[9,23,38,49,54,61,69,74,77,94,102,145,154,170],"dilemma":[10],"between":[11],"exploration":[12],"and":[13,31,133],"exploitation":[14],"in":[15,92,139],"sequential":[16],"decision":[17,24,62],"making.":[18],"At":[19],"every":[20],"time":[21],"step,":[22],"maker":[25,63],"selects":[26],"set":[28],"of":[29,37,48,60,96,125,147,172],"arms":[30,75,87,98,148],"observes":[32],"reward":[34],"from":[35],"each":[36],"chosen":[39],"arms.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,52,152],"present":[45],"variant":[47],"problem,":[50],"which":[51,128],"call":[53],"Scaling":[55],"MAB":[56],"(S-MAB):":[57],"goal":[59],"not":[65,100],"only":[66],"to":[67,83,88,108,136,149,163],"maximize":[68],"cumulative":[70],"rewards,":[71],"i.e.,":[72],"choosing":[73],"with":[76,157,165],"highest":[78],"expected":[79],"reward,":[80],"but":[81],"also":[82],"decide":[84],"how":[85],"many":[86,109],"select":[89],"so":[90],"that,":[91],"expectation,":[93],"cost":[95],"selecting":[97],"does":[99],"exceed":[101],"rewards.":[103],"This":[104],"problem":[105],"relevant":[107],"real-world":[110,177],"applications,":[111],"e.g.,":[112],"online":[113],"advertising,":[114],"financial":[115],"investments":[116],"or":[117],"data":[118],"stream":[119],"monitoring.":[120],"We":[121,168],"propose":[122],"an":[123],"extension":[124,142],"Thompson":[126],"Sampling,":[127],"has":[129],"strong":[130],"theoretical":[131],"guarantees":[132],"reported":[135],"perform":[137],"well":[138],"practice.":[140],"Our":[141],"dynamically":[143],"controls":[144],"number":[146],"draw.":[150],"Furthermore,":[151],"combine":[153],"proposed":[155],"method":[156],"ADWIN,":[158],"state-of-the-art":[160],"change":[161],"detector,":[162],"deal":[164],"non-static":[166],"environments.":[167],"illustrate":[169],"benefits":[171],"our":[173],"contribution":[174],"via":[175],"use":[178],"case":[179],"on":[180],"predictive":[181],"maintenance.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}