{"id":"https://openalex.org/W4401202539","doi":"https://doi.org/10.48550/arxiv.2407.20128","title":"Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games","display_name":"Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games","publication_year":2024,"publication_date":"2024-07-29","ids":{"openalex":"https://openalex.org/W4401202539","doi":"https://doi.org/10.48550/arxiv.2407.20128"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.20128","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.20128","pdf_url":"https://arxiv.org/pdf/2407.20128","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.20128","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017147474","display_name":"Fathima Zarin Faizal","orcid":"https://orcid.org/0000-0002-5663-8308"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Faizal, Fathima Zarin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067307504","display_name":"Asuman Ozdaglar","orcid":"https://orcid.org/0000-0002-1827-1285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozdaglar, Asuman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038379562","display_name":"Martin J. Wainwright","orcid":"https://orcid.org/0000-0002-8760-2236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wainwright, Martin J.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017147474"],"corresponding_institution_ids":[],"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":0.932699978351593,"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":0.932699978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6868165731430054},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6484469771385193},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5410704612731934},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5223132967948914},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.51922208070755},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.4939113259315491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43974992632865906},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3639053702354431},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.35840243101119995},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3315611481666565},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.2141796052455902},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17912045121192932},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16594600677490234}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6868165731430054},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6484469771385193},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5410704612731934},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5223132967948914},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.51922208070755},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.4939113259315491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43974992632865906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3639053702354431},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35840243101119995},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3315611481666565},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2141796052455902},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17912045121192932},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16594600677490234},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.20128","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.20128","pdf_url":"https://arxiv.org/pdf/2407.20128","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.20128","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.20128","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.20128","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.20128","pdf_url":"https://arxiv.org/pdf/2407.20128","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3487640509","display_name":null,"funder_award_id":"N00014-21-1-2842","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5269059174","display_name":"Non-parametric estimation under covariate shift: From fundamental bounds to efficient algorithms","funder_award_id":"2311072","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401202539.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2739681863","https://openalex.org/W3170723600","https://openalex.org/W4287122294","https://openalex.org/W2039187327","https://openalex.org/W2140409554","https://openalex.org/W1877069894","https://openalex.org/W2236801283","https://openalex.org/W1994737592","https://openalex.org/W3148329014","https://openalex.org/W3011680666"],"abstract_inverted_index":{"We":[0],"study":[1,108],"best-response":[2,116],"type":[3,21,117],"learning":[4,103,111],"dynamics":[5,112],"for":[6,119,143],"zero-sum":[7],"polymatrix":[8],"games":[9,105],"under":[10],"two":[11,15],"information":[12,23,41,66],"settings.":[13],"The":[14,35,60],"settings":[16],"are":[17,77],"distinguished":[18],"by":[19],"the":[20,29,39,64,97,102],"of":[22,80],"that":[24,113],"each":[25,45],"player":[26,46],"has":[27],"about":[28],"game":[30],"and":[31,50,55,76],"their":[32,48,51,73,88],"opponents'":[33,52,74],"strategy.":[34],"first":[36],"setting":[37,62],"is":[38,63],"full":[40],"case,":[42,67],"in":[43,101,104],"which":[44],"knows":[47],"own":[49],"payoff":[53,82,130],"matrices":[54,83],"observes":[56],"everyone's":[57],"mixed":[58],"strategies.":[59],"second":[61],"minimal":[65],"where":[68],"players":[69],"do":[70],"not":[71,78],"observe":[72,87],"strategies":[75],"aware":[79],"any":[81],"(instead":[84],"they":[85],"only":[86],"realized":[89],"payoffs).":[90],"For":[91,132],"this":[92],"setting,":[93],"also":[94],"known":[95],"as":[96],"radically":[98],"uncoupled":[99],"case":[100],"literature,":[106],"we":[107,138],"a":[109,123,128],"two-timescale":[110],"combine":[114],"smoothed":[115],"updates":[118],"strategy":[120],"estimates":[121],"with":[122],"TD-learning":[124],"update":[125],"to":[126,145],"estimate":[127],"local":[129],"function.":[131],"these":[133],"dynamics,":[134],"without":[135],"additional":[136],"exploration,":[137],"provide":[139],"polynomial-time":[140],"finite-sample":[141],"guarantees":[142],"convergence":[144],"an":[146],"$\u03b5$-Nash":[147],"equilibrium.":[148]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2024-08-01T00:00:00"}