{"id":"https://openalex.org/W4409157911","doi":"https://doi.org/10.1145/3690624.3709279","title":"Achieving Nearly-Optimal Regret and Sample Complexity in Dueling Bandits with Applications in Online Recommendations","display_name":"Achieving Nearly-Optimal Regret and Sample Complexity in Dueling Bandits with Applications in Online Recommendations","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409157911","doi":"https://doi.org/10.1145/3690624.3709279"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","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/A5071186810","display_name":"Lanjihong Ma","orcid":"https://orcid.org/0000-0001-7978-6146"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lanjihong Ma","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045601793","display_name":"Yao-Xiang Ding","orcid":"https://orcid.org/0000-0001-8580-1103"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao-Xiang Ding","raw_affiliation_strings":["State Key Lab of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389553","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0003-2101-1836"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhen-Yu Zhang","raw_affiliation_strings":["Center for Advanced Intelligence Project, RIKEN, Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project, RIKEN, Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621138","display_name":"Zhi\u2010Hua Zhou","orcid":"https://orcid.org/0000-0003-0746-1494"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Hua Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071186810"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08605238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1008","last_page":"1019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/regret","display_name":"Regret","score":0.884013295173645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5997534394264221},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5642312169075012},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4715091288089752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3154160976409912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24744415283203125}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.884013295173645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5997534394264221},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5642312169075012},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4715091288089752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3154160976409912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24744415283203125},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3690624.3709279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1518788040","https://openalex.org/W1553636730","https://openalex.org/W2009979684","https://openalex.org/W2015236210","https://openalex.org/W2038435918","https://openalex.org/W2044493620","https://openalex.org/W2094790959","https://openalex.org/W2106351931","https://openalex.org/W2233729533","https://openalex.org/W2358698356","https://openalex.org/W2395937008","https://openalex.org/W2560674852","https://openalex.org/W2595840341","https://openalex.org/W2614730337","https://openalex.org/W2739497747","https://openalex.org/W2803936341","https://openalex.org/W2809162153","https://openalex.org/W2883737864","https://openalex.org/W2949687195","https://openalex.org/W2970664163","https://openalex.org/W2978329087","https://openalex.org/W3006303816","https://openalex.org/W3085534303","https://openalex.org/W3215986094","https://openalex.org/W4226278401","https://openalex.org/W4254749579","https://openalex.org/W4289743144","https://openalex.org/W4290944323","https://openalex.org/W4299828299","https://openalex.org/W4310895557","https://openalex.org/W4378771755","https://openalex.org/W4410193499","https://openalex.org/W6603194324","https://openalex.org/W6632992360","https://openalex.org/W6679205030","https://openalex.org/W6691531235","https://openalex.org/W6712556327","https://openalex.org/W6743680971","https://openalex.org/W6755038633","https://openalex.org/W6796411177","https://openalex.org/W6803697455"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2971351794","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2963049774","https://openalex.org/W2106714532","https://openalex.org/W4297979791"],"abstract_inverted_index":{"We":[0],"focus":[1],"on":[2,43,170,232],"the":[3,23,37,67,85,98,108,114,132,135,147,158,227,242,245],"dueling":[4,58,154,161],"bandits":[5,155,162],"problem,":[6],"which":[7,63,80],"has":[8],"recently":[9],"drawn":[10],"significant":[11],"attention":[12],"due":[13],"to":[14,47,65,82,226],"its":[15],"wide-ranging":[16],"applications":[17],"in":[18,57,153,160],"online":[19,32,238],"recommendation":[20,239],"systems":[21],"and":[22,75,123,151,188,201,216,236],"alignment":[24],"of":[25,70,100,116,134,149,244],"large":[26],"language":[27],"models":[28],"(LLMs),":[29],"considers":[30],"an":[31],"preference":[33],"learning":[34],"scenario":[35],"where":[36],"learner":[38],"iteratively":[39],"selects":[40],"arms":[41,72],"based":[42],"pairwise":[44],"comparison":[45],"feedback":[46,111],"infer":[48],"user":[49,90],"preferences.":[50],"Two":[51],"primary":[52],"objectives":[53],"are":[54],"typically":[55],"considered":[56],"bandits:":[59],"Regret":[60],"Minimization":[61],"(RM),":[62],"aims":[64],"improve":[66],"overall":[68],"quality":[69],"selected":[71],"over":[73],"time,":[74],"Best":[76],"Arm":[77],"Identification":[78],"(BAI),":[79],"seeks":[81],"efficiently":[83],"identify":[84],"best":[86],"item":[87],"with":[88,193],"minimal":[89],"feedback.":[91],"For":[92],"instance,":[93],"RM":[94,122,150,182,195],"is":[95,223],"exemplified":[96],"by":[97,112,156],"objective":[99],"consistently":[101],"providing":[102,248],"high-quality":[103],"items,":[104],"while":[105],"BAI":[106,124,152,159,186,213],"reduces":[107],"required":[109],"human":[110],"minimizing":[113],"number":[115],"necessary":[117],"comparisons.":[118],"Conventional":[119],"research":[120],"treats":[121],"as":[125],"two":[126],"conflicting":[127],"objectives,":[128],"optimizing":[129],"one":[130],"at":[131],"expense":[133],"other.":[136],"In":[137],"this":[138],"paper,":[139],"we":[140,173],"propose":[141,174],"a":[142,164,175,185,211,218],"novel":[143],"framework":[144],"that":[145,179,190,222],"demonstrates":[146],"near-consistency":[148],"reducing":[157],"into":[163,184],"sequential":[165],"noisy":[166],"identification":[167],"problem.":[168],"Based":[169],"our":[171,252],"formulation,":[172],"black-box":[176],"reduction":[177,192],"technique":[178],"transforms":[180],"any":[181],"algorithm":[183,196,209],"algorithm,":[187],"prove":[189],"such":[191],"optimal":[194,198],"achieves":[197],"sample":[199,214],"complexity":[200,215],"nearly-optimal":[202,212],"cumulative":[203,219],"weak":[204,220],"regret":[205,221],"simultaneously.":[206,230],"Our":[207],"proposed":[208,246],"acheives":[210],"attains":[217],"order-wise":[224],"equivalent":[225],"best-known":[228],"result":[229],"Experiments":[231],"both":[233],"synthetic":[234],"benchmarks":[235],"real-world":[237],"tasks":[240],"validate":[241],"effectiveness":[243],"method,":[247],"empirical":[249],"evidences":[250],"for":[251],"theoretical":[253],"findings.":[254]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}