{"id":"https://openalex.org/W2964560279","doi":"https://doi.org/10.24963/ijcai.2019/450","title":"A Practical Semi-Parametric Contextual Bandit","display_name":"A Practical Semi-Parametric Contextual Bandit","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964560279","doi":"https://doi.org/10.24963/ijcai.2019/450","mag":"2964560279"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/450","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/450","pdf_url":"https://www.ijcai.org/proceedings/2019/0450.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0450.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039086738","display_name":"Yi Peng","orcid":"https://orcid.org/0000-0003-0373-6665"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Peng","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021904789","display_name":"Miao Xie","orcid":"https://orcid.org/0000-0002-9569-509X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Xie","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045982481","display_name":"Jiahao Liu","orcid":"https://orcid.org/0000-0003-1926-8448"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Liu","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101502904","display_name":"Xuying Meng","orcid":"https://orcid.org/0000-0002-0095-4811"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuying Meng","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341075","display_name":"Nan Li","orcid":"https://orcid.org/0000-0002-7588-8118"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"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/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Yang","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512133","display_name":"Tao Yao","orcid":"https://orcid.org/0000-0002-2124-5678"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yao","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"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/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Jin","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3246","last_page":"3252"},"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":0.9926000237464905,"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":0.9918000102043152,"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/regret","display_name":"Regret","score":0.9485555291175842},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7512669563293457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6818707585334778},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.565261721611023},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5596120357513428},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5328800082206726},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5071754455566406},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4693048298358917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3348385691642761},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2388092577457428},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22824454307556152}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9485555291175842},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7512669563293457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818707585334778},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.565261721611023},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5596120357513428},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5328800082206726},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5071754455566406},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4693048298358917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3348385691642761},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2388092577457428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22824454307556152},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/450","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/450","pdf_url":"https://www.ijcai.org/proceedings/2019/0450.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/450","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/450","pdf_url":"https://www.ijcai.org/proceedings/2019/0450.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964560279.pdf","grobid_xml":"https://content.openalex.org/works/W2964560279.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W148122774","https://openalex.org/W285554160","https://openalex.org/W1487320471","https://openalex.org/W1900560890","https://openalex.org/W2039522160","https://openalex.org/W2093562354","https://openalex.org/W2099679938","https://openalex.org/W2108114251","https://openalex.org/W2112420033","https://openalex.org/W2128421120","https://openalex.org/W2166253248","https://openalex.org/W2168405694","https://openalex.org/W2185823609","https://openalex.org/W2400213106","https://openalex.org/W2443763917","https://openalex.org/W2764809058","https://openalex.org/W2793172510","https://openalex.org/W2905520682","https://openalex.org/W2963679915","https://openalex.org/W2963964957","https://openalex.org/W2964240248","https://openalex.org/W3121632328","https://openalex.org/W4234228486","https://openalex.org/W4299286629"],"related_works":["https://openalex.org/W2289718384","https://openalex.org/W1995675544","https://openalex.org/W2158905189","https://openalex.org/W4319874546","https://openalex.org/W2509524819","https://openalex.org/W2012121796","https://openalex.org/W2068427817","https://openalex.org/W2952090425","https://openalex.org/W2538333368","https://openalex.org/W3127866798"],"abstract_inverted_index":{"Classic":[0],"multi-armed":[1],"bandit":[2,17],"algorithms":[3,18],"are":[4,19,54,73],"inefficient":[5],"for":[6,79,150],"a":[7,26,92,105,128,157,168],"large":[8,27],"number":[9],"of":[10,33,156,173,182],"arms.":[11],"On":[12],"the":[13,31,80,133,174,179],"other":[14],"hand,":[15],"contextual":[16],"more":[20,141],"efficient,":[21],"but":[22],"they":[23,50],"suffer":[24],"from":[25,171],"regret":[28],"due":[29],"to":[30,46,98,122,137],"bias":[32],"reward":[34],"estimation":[35],"with":[36,127,152],"finite":[37],"dimensional":[38,154],"features.":[39],"Although":[40],"recent":[41],"studies":[42],"proposed":[43,149],"semi-parametric":[44],"bandits":[45],"overcome":[47],"these":[48],"defects,":[49],"assume":[51],"arms'":[52],"features":[53,155],"constant":[55],"over":[56,76],"time.":[57],"However,":[58],"this":[59,88,100,103],"assumption":[60],"rarely":[61],"holds":[62],"in":[63,143],"practice,":[64],"since":[65],"real-world":[66],"problems":[67],"often":[68],"involve":[69],"underlying":[70],"processes":[71],"that":[72],"dynamically":[74],"evolving":[75],"time":[77],"especially":[78],"special":[81],"promotions":[82],"like":[83],"Singles'":[84],"Day":[85],"sales.":[86],"In":[87],"paper,":[89],"we":[90],"formulate":[91],"novel":[93,106],"Semi-Parametric":[94,112],"Contextual":[95],"Bandit":[96],"Problem":[97],"relax":[99],"assumption.":[101],"For":[102],"problem,":[104],"Two-Steps":[107],"Upper-Confidence":[108],"Bound":[109],"framework,":[110],"called":[111],"UCB":[113],"(SPUCB),":[114],"is":[115,148],"presented.":[116],"It":[117],"can":[118],"be":[119],"flexibly":[120],"applied":[121],"linear":[123,158],"parametric":[124],"function":[125],"problem":[126],"satisfied":[129],"gap-free":[130],"bound":[131],"on":[132,162],"n-step":[134],"regret.":[135],"Moreover,":[136],"make":[138],"our":[139,183],"method":[140],"practical":[142],"online":[144],"system,":[145],"an":[146],"optimization":[147],"dealing":[151],"high":[153],"function.":[159],"Extensive":[160],"experiments":[161],"synthetic":[163],"data":[164],"as":[165,167],"well":[166],"real":[169],"dataset":[170],"one":[172],"largest":[175],"e-commercial":[176],"platforms":[177],"demonstrate":[178],"superior":[180],"performance":[181],"algorithm.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}