{"id":"https://openalex.org/W4225624975","doi":"https://doi.org/10.24963/ijcai.2022/515","title":"Improved Pure Exploration in Linear Bandits with No-Regret Learning","display_name":"Improved Pure Exploration in Linear Bandits with No-Regret Learning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4225624975","doi":"https://doi.org/10.24963/ijcai.2022/515"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/515","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/515","pdf_url":"https://www.ijcai.org/proceedings/2022/0515.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0515.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022610118","display_name":"Mohammadi Zaki","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mohammadi Zaki","raw_affiliation_strings":["Indian Institute of Science (IISc), Bangalore"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc), Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062911903","display_name":"Avi Mohan","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avi Mohan","raw_affiliation_strings":["Boston University, MA"],"affiliations":[{"raw_affiliation_string":"Boston University, MA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030430086","display_name":"Aditya Gopalan","orcid":"https://orcid.org/0000-0002-7323-2975"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Gopalan","raw_affiliation_strings":["Indian Institute of Science (IISc), Bangalore"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc), Bangalore","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022610118"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04656085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3709","last_page":"3715"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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/regret","display_name":"Regret","score":0.7855719923973083},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5297133922576904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.526491105556488},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5098406672477722},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5075937509536743},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.47349461913108826},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4210089147090912},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.41741156578063965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41247910261154175},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.345872163772583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19143807888031006}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7855719923973083},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5297133922576904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.526491105556488},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5098406672477722},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5075937509536743},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.47349461913108826},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4210089147090912},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.41741156578063965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41247910261154175},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.345872163772583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19143807888031006},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/515","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/515","pdf_url":"https://www.ijcai.org/proceedings/2022/0515.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai::77250","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/515","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/515","pdf_url":"https://www.ijcai.org/proceedings/2022/0515.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First 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/W4225624975.pdf","grobid_xml":"https://content.openalex.org/works/W4225624975.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2012731843","https://openalex.org/W2106663919","https://openalex.org/W2147967768","https://openalex.org/W2149107760","https://openalex.org/W2165856466","https://openalex.org/W2168810201","https://openalex.org/W2255843478","https://openalex.org/W2293239647","https://openalex.org/W2765335312","https://openalex.org/W2804342876","https://openalex.org/W2925540570","https://openalex.org/W2950319173","https://openalex.org/W2951665052","https://openalex.org/W2954234600","https://openalex.org/W2970271647","https://openalex.org/W3008801451","https://openalex.org/W3035083041","https://openalex.org/W3038036515","https://openalex.org/W3124229194","https://openalex.org/W3212992834","https://openalex.org/W4288028707","https://openalex.org/W4288320205","https://openalex.org/W4292022450","https://openalex.org/W4299548526","https://openalex.org/W6779806053","https://openalex.org/W6864014924"],"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/W2990709181","https://openalex.org/W2963049774"],"abstract_inverted_index":{"We":[0,37,151,194],"study":[1],"the":[2,13,21,77,80,90,103,141,154,179,200],"best":[3,48],"arm":[4,49],"identification":[5],"problem":[6,22,118],"in":[7,12,113,122,164],"linear":[8,27,174],"multi-armed":[9],"bandits":[10],"(LMAB)":[11],"fixed":[14],"confidence":[15,100],"setting":[16],";":[17],"this":[18,192],"is":[19,119,145,177],"also":[20,195],"of":[23,73,79,140,157],"optimizing":[24],"an":[25,39,74,148,168],"unknown":[26,81,104,142],"function":[28],"over":[29],"a":[30,62,98,116,136,165],"discrete":[31],"domain":[32],"with":[33,204],"noisy,":[34],"zeroth-order":[35],"access.":[36],"propose":[38],"explicitly":[40],"implementable":[41],"and":[42,69,106,144,163,188],"provably":[43],"order-optimal":[44,185],"sample-complexity":[45],"algorithm":[46,181,202],"for":[47,173,191,199],"identification.":[50],"Existing":[51],"approaches":[52],"that":[53,153],"achieve":[54,183],"optimal":[55],"sample":[56,155,186],"complexity":[57,156,187],"assume":[58],"either":[59],"access":[60],"to":[61,109,134,161,182],"nontrivial":[63],"minimax":[64,117],"optimization":[65],"oracle":[66],"(e.g.":[67],"RAGE":[68],"Lazy-TS)":[70],"or":[71],"knowledge":[72],"upper-bound":[75],"on":[76,138],"norm":[78,139],"parameter":[82],"vector(e.g.":[83],"LinGame).":[84],"Our":[85],"algorithm,":[86],"which":[87],"we":[88],"call":[89],"Phased":[91],"Elimination":[92],"Linear":[93],"Exploration":[94],"Game":[95],"(PELEG),":[96],"maintains":[97],"high-probability":[99],"ellipsoid":[101],"containing":[102],"vector,":[105,143],"uses":[107],"it":[108],"eliminate":[110],"suboptimal":[111],"arms":[112],"phases,":[114],"where":[115],"essentially":[120],"solved":[121],"each":[123],"phase":[124],"using":[125],"two-player":[126],"low":[127],"regret":[128],"learners.":[129],"PELEG":[130,158,176],"does":[131],"not":[132],"require":[133],"know":[135],"bound":[137,172],"asymptotically-optimal,":[146],"settling":[147],"open":[149],"problem.":[150],"show":[152],"matches,":[159],"up":[160],"order":[162],"non-asymptotic":[166],"sense,":[167],"instance-dependent":[169],"universal":[170],"lower":[171],"bandits.":[175],"thus":[178],"first":[180],"both":[184],"explicit":[189],"implementability":[190],"setting.":[193],"provide":[196],"numerical":[197],"results":[198],"proposed":[201],"consistent":[203],"its":[205],"theoretical":[206],"guarantees.":[207]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}