{"id":"https://openalex.org/W4412377112","doi":"https://doi.org/10.1145/3726302.3730176","title":"Counterfactual Model Selection in Contextual Bandits","display_name":"Counterfactual Model Selection in Contextual Bandits","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377112","doi":"https://doi.org/10.1145/3726302.3730176"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730176","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730176","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730176","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730176","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081318753","display_name":"Shion Ishikawa","orcid":"https://orcid.org/0009-0007-4326-8348"},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shion Ishikawa","raw_affiliation_strings":["Rakuten Group, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0007-4326-8348","affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079813006","display_name":"Yee Ming Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Young-joo Chung","raw_affiliation_strings":["Rakuten Group, Inc., San Mateo, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-8430-5391","affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc., San Mateo, CA, USA","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039810398","display_name":"Y. Liu","orcid":"https://orcid.org/0009-0006-4583-5716"},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yun-Ching Liu","raw_affiliation_strings":["Rakuten Group, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0006-4583-5716","affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043297373","display_name":"Yu Hirate","orcid":"https://orcid.org/0009-0004-0362-7156"},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Hirate","raw_affiliation_strings":["Rakuten Group, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0004-0362-7156","affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I1301041018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18073506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2597","last_page":"2601"},"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":0.9987000226974487,"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":0.9887999892234802,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8365379571914673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7295559048652649},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6590360403060913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5264699459075928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36437129974365234},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09351760149002075}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8365379571914673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7295559048652649},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6590360403060913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264699459075928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36437129974365234},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09351760149002075},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730176","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730176","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730176","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730176","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730176","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730176","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377112.pdf","grobid_xml":"https://content.openalex.org/works/W4412377112.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1514587017","https://openalex.org/W2029604041","https://openalex.org/W2077902449","https://openalex.org/W2150291618","https://openalex.org/W2168405694","https://openalex.org/W2752599163","https://openalex.org/W2755613412","https://openalex.org/W2773557179","https://openalex.org/W2914304175","https://openalex.org/W3009712390","https://openalex.org/W3197958031","https://openalex.org/W3201265114","https://openalex.org/W4310813832","https://openalex.org/W6730352657"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Contextual":[0],"bandit":[1,28,40],"algorithms":[2,29,41],"are":[3],"crucial":[4],"in":[5,24,45,83],"various":[6,25],"decision-making":[7],"applications,":[8],"such":[9,55],"as":[10,56],"personalized":[11],"content":[12],"recommendation,":[13],"online":[14],"advertising,":[15],"and":[16,58,114,131,146,154,160,168],"e-commerce":[17],"banner":[18],"placement.":[19],"Despite":[20],"their":[21],"successful":[22],"applications":[23],"domains,":[26],"contextual":[27,84],"still":[30],"face":[31],"significant":[32],"challenges":[33],"with":[34],"exploration":[35,44],"efficiency":[36],"compared":[37],"to":[38,43,63,77,96,105],"non-contextual":[39],"due":[42],"feature":[46],"spaces.":[47],"To":[48],"overcome":[49],"this":[50,69],"issue,":[51],"model":[52,80,106,120,142],"selection":[53,81,121],"policies":[54],"MetaEXP":[57,167],"MetaCORRAL":[59],"have":[60],"been":[61],"proposed":[62],"interactively":[64],"explore":[65],"base":[66,99],"policies.":[67],"In":[68],"paper,":[70],"we":[71],"introduce":[72],"a":[73,147,151],"novel":[74],"counterfactual":[75],"approach":[76,90],"address":[78],"the":[79,133,155],"problem":[82],"bandits.":[85],"Unlike":[86],"previous":[87],"methods,":[88],"our":[89,141],"leverages":[91],"unbiased":[92],"Off-Policy":[93],"Evaluation":[94],"(OPE)":[95],"dynamically":[97],"select":[98],"policies,":[100,165],"making":[101],"it":[102],"more":[103],"robust":[104],"misspecification.":[107],"We":[108,123,139],"present":[109],"two":[110],"new":[111],"algorithms,":[112],"MetaEXP-OPE":[113,159],"MetaGreedy-OPE,":[115],"which":[116],"utilize":[117],"OPE":[118,137],"for":[119],"policy.":[122],"also":[124],"provide":[125],"theoretical":[126],"analysis":[127],"on":[128,143],"regret":[129],"bounds":[130],"evaluate":[132],"impact":[134],"of":[135],"different":[136],"estimators.":[138],"evaluated":[140],"synthetic":[144],"data":[145],"semi-synthetic":[148],"simulator":[149],"using":[150],"real-world":[152],"dataset,":[153],"results":[156],"show":[157],"that":[158],"MetaGreedy-OPE":[161],"significantly":[162],"outperform":[163],"existing":[164],"including":[166],"MetaCORRAL.":[169]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}