{"id":"https://openalex.org/W7220930971","doi":"https://doi.org/10.48550/arxiv.2610.07737","title":"Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret","display_name":"Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220930971","doi":"https://doi.org/10.48550/arxiv.2610.07737"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.07737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07737","pdf_url":"https://arxiv.org/pdf/2610.07737","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/2610.07737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101622808","display_name":"Avishek Ghosh","orcid":"https://orcid.org/0000-0002-6548-6692","observed_orcids":["https://orcid.org/0000-0002-6548-6692"]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ghosh, Avishek","raw_affiliation_strings":["Department of Computer Science and Engineering Indian Institute of Technology , Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Indian Institute of Technology , Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101622808"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nash-social-welfare","display_name":"Nash social welfare","score":0.8939999938011169},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.9129999876022339},{"id":"https://openalex.org/keywords/regret-minimization","display_name":"regret minimization","score":0.5440000295639038},{"id":"https://openalex.org/keywords/minimax-lower-bounds","display_name":"minimax lower bounds","score":0.6570000052452087},{"id":"https://openalex.org/keywords/am-gm-inequality","display_name":"AM-GM inequality","score":0.8220000267028809}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8772000074386597},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.678600013256073},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.614300012588501},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5203999876976013},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.5009999871253967},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C22349654","wikidata":"https://www.wikidata.org/wiki/Q2039354","display_name":"Risk dominance","level":5,"score":0.4708000123500824},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.43689998984336853},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3903999924659729},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C40222840","wikidata":"https://www.wikidata.org/wiki/Q185049","display_name":"Geometric mean","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C90376892","wikidata":"https://www.wikidata.org/wiki/Q1516247","display_name":"Bargaining problem","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C163630976","wikidata":"https://www.wikidata.org/wiki/Q964667","display_name":"Correlated equilibrium","level":5,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.07737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07737","pdf_url":"https://arxiv.org/pdf/2610.07737","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.2610.07737","doi":"https://doi.org/10.48550/arxiv.2610.07737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.07737","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:2610.07737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07737","pdf_url":"https://arxiv.org/pdf/2610.07737","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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220930971.pdf","grobid_xml":"https://content.openalex.org/works/W7220930971.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1983387475","https://openalex.org/W2034489173","https://openalex.org/W2087443216","https://openalex.org/W2734285318","https://openalex.org/W2950929549","https://openalex.org/W2989932743","https://openalex.org/W3124038879","https://openalex.org/W4382239081","https://openalex.org/W7101394662","https://openalex.org/W7103748079","https://openalex.org/W7127122051"],"related_works":["https://openalex.org/W4382239081","https://openalex.org/W7101394662","https://openalex.org/W7103748079","https://openalex.org/W3212608195","https://openalex.org/W7127122051","https://openalex.org/W4382463371","https://openalex.org/W7133238895","https://openalex.org/W7169072442","https://openalex.org/W6979317878","https://openalex.org/W7160851348"],"abstract_inverted_index":{"We":[0,79,119,162],"study":[1],"fair":[2,140],"multi-armed":[3],"bandits":[4],"under":[5],"the":[6,16,37,41,48,53,62,70,76,92,133,176,181],"Nash":[7,25,82,124,147,157],"Social":[8],"Welfare":[9],"(NSW)":[10],"objective,":[11],"which":[12,90],"measures":[13],"performance":[14],"via":[15,190],"geometric":[17,54,93],"mean":[18,38,55,94],"of":[19,40,65],"accumulated":[20],"rewards.":[21],"Existing":[22],"work":[23],"defines":[24],"regret":[26,137],"as":[27],"$\\mathrm{NR}_T":[28],"=":[29,85,127],"\u03bc^\\star":[30,86,128],"-":[31,87,129],"(\\prod_{t=1}^T":[32],"\\mathbb{E}\u03bc_{I_t})^{1/T}$,":[33],"where":[34],"$\u03bc_{I_t}$":[35],"is":[36,47],"reward":[39],"recommended":[42],"arm":[43],"$I_t$":[44],"and":[45,192],"$T$":[46],"horizon.":[49],"Since":[50],"it":[51,60,114],"applies":[52],"to":[56],"per-round":[57],"marginal":[58],"expectations,":[59,101],"ignores":[61],"joint":[63],"distribution":[64],"rewards":[66],"across":[67],"rounds,":[68],"leaving":[69],"NSW":[71,103],"fairness":[72,104],"motivation":[73],"unaddressed":[74],"at":[75],"trajectory":[77],"level.":[78],"propose":[80],"\\emph{trajectory-wise":[81],"regret}":[83,125],"$\\widetilde{\\mathrm{NR}}_T":[84,110,164],"\\mathbb{E}[(\\prod_{t=1}^T":[88],"\u03bc_{I_t})^{1/T}]$,":[89],"computes":[91],"over":[95],"complete":[96],"sample":[97],"paths":[98],"before":[99],"taking":[100],"capturing":[102],"more":[105],"faithfully.":[106],"By":[107],"Jensen's":[108],"inequality,":[109],"\\geq":[111],"\\mathrm{NR}_T$,":[112],"making":[113],"a":[115,156,187],"strictly":[116],"stronger":[117,182],"metric.":[118],"also":[120],"introduce":[121],"\\emph{high":[122],"probability":[123,136,170],"$\\widehat{\\mathrm{NR}}_T":[126,172],"(\\prod_t":[130],"\u03bc_{I_t})^{1/T}$,":[131],"giving":[132],"first":[134],"high":[135],"bounds":[138],"in":[139],"bandits.":[141],"Our":[142],"two-phase":[143],"algorithm,":[144],"Round":[145],"Robin":[146],"Confidence":[148],"Bound":[149],"(\\texttt{RR-NCB}),":[150],"combines":[151],"round":[152],"robin":[153],"exploration":[154],"with":[155,169],"confidence":[158],"bound":[159,189],"index":[160],"policy.":[161],"show":[163],"\\leq":[165,173],"\\widetilde{\\mathcal{O}}(\\sqrt{k\\log":[166],"T/T})$":[167],"and,":[168],"$1-\u03b4$,":[171],"\\widetilde{\\mathcal{O}}(\\sqrt{k\\log(kT/\u03b4)/T})$,":[174],"matching":[175],"optimal":[177],"$\\widetilde{\\mathcal{O}}(\\sqrt{k/T})$":[178],"rate":[179],"despite":[180],"metrics.":[183],"Optimality":[184],"follows":[185],"from":[186],"lower":[188],"AM-GM":[191],"standard":[193],"$k$-armed":[194],"bandit":[195],"minimax":[196],"arguments.":[197],"Simulations":[198],"validate":[199],"our":[200],"theory.":[201]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}