{"id":"https://openalex.org/W4367310426","doi":"https://doi.org/10.1145/3543873.3587653","title":"Robust Stochastic Multi-Armed Bandits with Historical Data","display_name":"Robust Stochastic Multi-Armed Bandits with Historical Data","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367310426","doi":"https://doi.org/10.1145/3543873.3587653"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3587653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3587653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","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/A5009255756","display_name":"Sarah Boufelja Yacobi","orcid":"https://orcid.org/0000-0002-5197-5655"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sarah Boufelja Yacobi","raw_affiliation_strings":["Imperial College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055394860","display_name":"Djallel Bouneffouf","orcid":"https://orcid.org/0000-0003-3342-7513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Djallel Bouneffouf","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009255756"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.2547,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54783143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"959","last_page":"965"},"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":0.9955000281333923,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.760098934173584},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7180886268615723},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6315845251083374},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5154448747634888},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5031988024711609},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5030655264854431},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37970203161239624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.333607941865921},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28377753496170044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11724629998207092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760098934173584},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7180886268615723},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6315845251083374},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5154448747634888},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5031988024711609},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5030655264854431},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37970203161239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.333607941865921},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28377753496170044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11724629998207092},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543873.3587653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3587653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1094752974","https://openalex.org/W1998427280","https://openalex.org/W2009551863","https://openalex.org/W2031155969","https://openalex.org/W2061753713","https://openalex.org/W2092898315","https://openalex.org/W2112420033","https://openalex.org/W2150291618","https://openalex.org/W2158807713","https://openalex.org/W2168405694","https://openalex.org/W2767023880","https://openalex.org/W3098679278","https://openalex.org/W3150893739"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W118270247"],"abstract_inverted_index":{"We":[0,79,105],"consider":[1],"the":[2,29,43,57,60,63],"problem":[3],"of":[4,21,31,47,62],"Stochastic":[5],"Contextual":[6],"Multi-Armed":[7],"Bandits":[8],"(CMABs)":[9],"initialised":[10],"with":[11,15,90,100],"Historical":[12],"data.":[13],"Initialisation":[14],"historical":[16,91,102],"data":[17,77,92,103],"is":[18],"an":[19],"example":[20],"data-driven":[22],"regularisation":[23],"which":[24,50],"should,":[25],"in":[26,34],"theory,":[27],"accelerate":[28],"convergence":[30,58],"CMABs.":[32],"However,":[33],"practice,":[35],"we":[36,68],"have":[37],"little":[38],"to":[39,84],"no":[40],"control":[41],"over":[42],"underlying":[44],"generation":[45],"process":[46],"such":[48],"data,":[49],"may":[51],"exhibit":[52],"some":[53],"pathologies,":[54],"possibly":[55],"impeding":[56],"and":[59,76,93,97,111],"stability":[61],"algorithm.":[64],"In":[65],"this":[66],"paper,":[67],"focus":[69],"on":[70],"two":[71,81],"main":[72],"challenges:":[73],"bias":[74],"selection":[75],"corruption.":[78],"propose":[80],"new":[82],"algorithms":[83],"solve":[85],"these":[86],"specific":[87],"issues:":[88],"LinUCB":[89,99],"offline":[94],"balancing":[95],"(OB-HLinUCB)":[96],"Robust":[98],"corrupted":[101],"(R-HLinUCB).":[104],"derive":[106],"their":[107,113],"theoretical":[108],"regret":[109],"bounds":[110],"discuss":[112],"computational":[114],"performance":[115],"using":[116],"real-world":[117],"datasets.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}