{"id":"https://openalex.org/W2905520682","doi":"https://doi.org/10.1609/aaai.v33i01.33017933","title":"Semi-Parametric Sampling for Stochastic Bandits with Many Arms","display_name":"Semi-Parametric Sampling for Stochastic Bandits with Many Arms","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2905520682","doi":"https://doi.org/10.1609/aaai.v33i01.33017933","mag":"2905520682"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33017933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017933","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4793/4671","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4793/4671","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007900661","display_name":"Mingdong Ou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mingdong Ou","raw_affiliation_strings":["Alibaba"],"affiliations":[{"raw_affiliation_string":"Alibaba","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341075","display_name":"Nan Li","orcid":"https://orcid.org/0009-0003-9255-259X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060417049","display_name":"Cheng Yang","orcid":"https://orcid.org/0000-0001-7821-0030"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Yang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103861122","display_name":"Shenghuo Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shenghuo Zhu","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069394608","display_name":"Rong Jin","orcid":"https://orcid.org/0000-0002-8797-4646"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rong Jin","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007900661"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5711,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80170213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"33","issue":"01","first_page":"7933","last_page":"7940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9865000247955322,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9684000015258789,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.8091737031936646},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7690465450286865},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.6971185803413391},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.6373268961906433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6065508127212524},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.5151544809341431},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5124928951263428},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.500582218170166},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4567625820636749},{"id":"https://openalex.org/keywords/semiparametric-model","display_name":"Semiparametric model","score":0.4173470735549927},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4126723110675812},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4106805920600891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3280297815799713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2643101215362549},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20997482538223267},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.1138540506362915},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10649675130844116}],"concepts":[{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.8091737031936646},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7690465450286865},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.6971185803413391},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.6373268961906433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6065508127212524},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.5151544809341431},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5124928951263428},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.500582218170166},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4567625820636749},{"id":"https://openalex.org/C78297888","wikidata":"https://www.wikidata.org/wiki/Q7449607","display_name":"Semiparametric model","level":3,"score":0.4173470735549927},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4126723110675812},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4106805920600891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3280297815799713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2643101215362549},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20997482538223267},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.1138540506362915},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10649675130844116},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33017933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017933","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4793/4671","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33017933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017933","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4793/4671","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2905520682.pdf","grobid_xml":"https://content.openalex.org/works/W2905520682.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W1487320471","https://openalex.org/W1570738427","https://openalex.org/W1571154989","https://openalex.org/W1579652926","https://openalex.org/W2039522160","https://openalex.org/W2049934117","https://openalex.org/W2061753713","https://openalex.org/W2108114251","https://openalex.org/W2111241577","https://openalex.org/W2112420033","https://openalex.org/W2119738618","https://openalex.org/W2140660245","https://openalex.org/W2149721706","https://openalex.org/W2160163723","https://openalex.org/W2166253248","https://openalex.org/W2166566250","https://openalex.org/W2182000050","https://openalex.org/W2592998600","https://openalex.org/W2625190553","https://openalex.org/W2752599163","https://openalex.org/W2790576010","https://openalex.org/W2793172510","https://openalex.org/W2809005670","https://openalex.org/W2962901934","https://openalex.org/W2963561234","https://openalex.org/W2963964957","https://openalex.org/W2964278893","https://openalex.org/W3121632328","https://openalex.org/W3122984207","https://openalex.org/W4234228486","https://openalex.org/W4242941051","https://openalex.org/W4294249885","https://openalex.org/W4297732237","https://openalex.org/W4299286629","https://openalex.org/W4300223101","https://openalex.org/W6629353124","https://openalex.org/W6665861923","https://openalex.org/W6682160587","https://openalex.org/W6683757025","https://openalex.org/W6725739255","https://openalex.org/W6736081208","https://openalex.org/W6744205760","https://openalex.org/W6749557911","https://openalex.org/W7075680496"],"related_works":["https://openalex.org/W1850547517","https://openalex.org/W2034648278","https://openalex.org/W2964125852","https://openalex.org/W3176022311","https://openalex.org/W3046298489","https://openalex.org/W3048056964","https://openalex.org/W4287690869","https://openalex.org/W3122670876","https://openalex.org/W2156593932","https://openalex.org/W1485223389"],"abstract_inverted_index":{"We":[0,154],"consider":[1],"the":[2,33,70,102,106,141,150,168,198,201],"stochastic":[3],"bandit":[4,17,52],"problem":[5],"with":[6,48,187],"a":[7,44,86,116],"large":[8,34,63],"candidate":[9,128,152],"arm":[10,40,49,120],"set.":[11,129],"In":[12,81,171],"this":[13,82,95],"setting,":[14],"classic":[15],"multi-armed":[16],"algorithms,":[18],"which":[19,97,111,135,163],"assume":[20],"independence":[21],"among":[22],"arms":[23,126],"and":[24],"adopt":[25],"non-parametric":[26,131],"reward":[27,46,71,103,114,138],"model,":[28,139],"are":[29,54],"inefficient,":[30],"due":[31,68],"to":[32,69,144],"number":[35],"of":[36,109,119,133,158,200],"arms.":[37,153],"By":[38],"exploiting":[39],"correlations":[41],"based":[42],"on":[43,149],"parametric":[45,107,117,142,169],"model":[47,76],"features,":[50],"contextual":[51],"algorithms":[53],"more":[55],"efficient,":[56],"but":[57],"they":[58],"can":[59,122],"also":[60],"suffer":[61],"from":[62,74,127],"regret":[64,181],"in":[65],"practical":[66],"applications,":[67],"estimation":[72,143,146],"bias":[73],"mis-specified":[75],"assumption":[77],"or":[78],"incomplete":[79],"features.":[80],"paper,":[83],"we":[84],"propose":[85],"novel":[87],"Bayesian":[88],"framework,":[89],"called":[90],"Semi-Parametric":[91],"Sampling":[92],"(SPS),":[93],"for":[94],"problem,":[96],"employs":[98],"semi-parametric":[99,172],"function":[100,118,166],"as":[101,115,167],"model.":[104],"Specifically,":[105],"part":[108,132],"SPS,":[110,134,159],"models":[112],"expected":[113],"feature,":[121],"efficiently":[123],"eliminate":[124],"poor":[125],"The":[130],"adopts":[136],"nonparametric":[137],"revises":[140],"avoid":[145],"bias,":[147],"especially":[148],"remained":[151],"give":[155],"an":[156],"implementation":[157],"Linear":[160],"SPS":[161],"(LSPS),":[162],"utilizes":[164],"linear":[165],"part.":[170],"environment,":[173],"theoretical":[174],"analysis":[175],"shows":[176],"that":[177],"LSPS":[178],"achieves":[179],"better":[180],"bound":[182],"(i.e.":[183],"O\u0334(\u221aN1\u2212\u03b1":[184],"d\u03b1":[185],"\u221aT)":[186],"\u03b1":[188],"\u2208":[189],"[0,":[190],"1]))":[191],"than":[192],"existing":[193],"approaches.":[194],"Also,":[195],"experiments":[196],"demonstrate":[197],"superiority":[199],"proposed":[202],"approach.":[203]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}