{"id":"https://openalex.org/W7220922650","doi":"https://doi.org/10.48550/arxiv.2610.09929","title":"Expected Sample Complexity in Multi-Armed Bandits","display_name":"Expected Sample Complexity in Multi-Armed Bandits","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220922650","doi":"https://doi.org/10.48550/arxiv.2610.09929"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09929","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09929","pdf_url":"https://arxiv.org/pdf/2610.09929","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09929","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157964015","display_name":"Nadav Sukenik","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sukenik, Nadav","raw_affiliation_strings":["Technion -Institute of Technology Technion -Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion -Institute of Technology Technion -Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018784842","display_name":"Nadav Merlis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Merlis, Nadav","raw_affiliation_strings":["Technion -Institute of Technology Technion -Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion -Institute of Technology Technion -Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.0,"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/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.890999972820282},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.9670000076293945},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.9990000128746033},{"id":"https://openalex.org/keywords/lower-bounds","display_name":"lower bounds","score":0.6029999852180481},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.6299999952316284}],"concepts":[{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.6662999987602234},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.640999972820282},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5583000183105469},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3537999987602234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C95763700","wikidata":"https://www.wikidata.org/wiki/Q578985","display_name":"Convergence of random variables","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C141042865","wikidata":"https://www.wikidata.org/wiki/Q200125","display_name":"Expected value","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C97399411","wikidata":"https://www.wikidata.org/wiki/Q825367","display_name":"Coin flipping","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09929","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09929","pdf_url":"https://arxiv.org/pdf/2610.09929","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.09929","doi":"https://doi.org/10.48550/arxiv.2610.09929","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09929","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.09929","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09929","pdf_url":"https://arxiv.org/pdf/2610.09929","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220922650.pdf","grobid_xml":"https://content.openalex.org/works/W7220922650.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2942494530","https://openalex.org/W4391245004"],"related_works":["https://openalex.org/W2132876566","https://openalex.org/W2210427546","https://openalex.org/W2951812322","https://openalex.org/W1911551976","https://openalex.org/W268671474","https://openalex.org/W1849231985","https://openalex.org/W4221157193","https://openalex.org/W4225508619","https://openalex.org/W7100933069","https://openalex.org/W7098749886"],"abstract_inverted_index":{"Sample":[0],"complexity":[1,31,42,149],"is":[2,122,130],"a":[3,48,173],"widely":[4],"used":[5],"metric":[6],"in":[7,47,54,71,77,97,113,141,169],"sequential":[8],"decision-making":[9],"problems,":[10],"defined":[11],"as":[12],"the":[13,19,22,29,39,67,117,125,133,142,146,165,177],"number":[14],"of":[15,32,150],"suboptimal":[16],"decisions":[17],"during":[18],"interaction":[20],"between":[21,176],"agent":[23],"and":[24,37,80,109,127,140,171],"an":[25,137],"environment.":[26],"We":[27,57,93],"study":[28],"sample":[30,41,148],"stochastic":[33,111],"multi-armed":[34],"bandit":[35],"problems":[36],"introduce":[38],"expected":[40,69,90,147],"performance":[43,174],"measure,":[44],"analyzing":[45],"it":[46,129],"novel":[49],"framework":[50],"called":[51],"approximately":[52],"correct":[53],"expectation":[55],"(ACE).":[56],"show":[58,82,95],"that":[59,164],"ACE":[60,86,107],"guarantees":[61,75,87],"imply":[62],"almost":[63],"sure":[64],"convergence":[65],"to":[66,73,84,99,124],"optimal":[68],"reward,":[70],"contrast":[72,98],"high-probability":[74],"found":[76],"other":[78],"frameworks,":[79],"also":[81],"how":[83],"convert":[85],"into":[88],"explicit":[89],"regret":[91],"bounds.":[92],"further":[94],"that,":[96],"existing":[100],"measures,":[101],"deterministic":[102],"algorithms":[103,112,166],"cannot":[104],"obtain":[105],"favorable":[106],"bounds,":[108],"analyze":[110,145],"two":[114,178],"settings:":[115],"when":[116,128],"allowed":[118],"suboptimality":[119],"level":[120],"$\u03b5$":[121,170],"known":[123],"algorithm":[126],"unknown.":[131],"In":[132],"former,":[134],"we":[135,144,154],"devise":[136],"explore-then-$\u03b5$-greedy":[138],"algorithm,":[139],"latter,":[143],"Thompson":[151],"sampling.":[152],"Finally,":[153],"establish":[155],"nearly":[156],"matching":[157],"lower":[158],"bounds":[159],"for":[160],"both":[161],"settings,":[162],"showing":[163],"are":[167],"tight":[168],"proving":[172],"separation":[175],"regimes.":[179]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}