{"id":"https://openalex.org/W4386066409","doi":"https://doi.org/10.1109/isit54713.2023.10206444","title":"Reward Teaching for Federated Multi-armed Bandits","display_name":"Reward Teaching for Federated Multi-armed Bandits","publication_year":2023,"publication_date":"2023-06-25","ids":{"openalex":"https://openalex.org/W4386066409","doi":"https://doi.org/10.1109/isit54713.2023.10206444"},"language":"en","primary_location":{"id":"doi:10.1109/isit54713.2023.10206444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit54713.2023.10206444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on Information Theory (ISIT)","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/A5082788397","display_name":"Chengshuai Shi","orcid":"https://orcid.org/0000-0002-2727-8251"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chengshuai Shi","raw_affiliation_strings":["University of Virginia,Charlottesville,VA,USA,22904"],"affiliations":[{"raw_affiliation_string":"University of Virginia,Charlottesville,VA,USA,22904","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020964161","display_name":"Wei Xiong","orcid":"https://orcid.org/0000-0003-1686-6477"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Xiong","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Hong Kong","The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016749653","display_name":"Cong Shen","orcid":"https://orcid.org/0000-0002-3148-4453"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Shen","raw_affiliation_strings":["University of Virginia,Charlottesville,VA,USA,22904"],"affiliations":[{"raw_affiliation_string":"University of Virginia,Charlottesville,VA,USA,22904","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645589","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0003-4439-6118"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]},{"id":"https://openalex.org/I4179309","display_name":"Park University","ror":"https://ror.org/04ngpga37","country_code":"US","type":"education","lineage":["https://openalex.org/I4179309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["The Pennsylvania State University, University Park,University Park,USA,16802"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park,University Park,USA,16802","institution_ids":["https://openalex.org/I130769515","https://openalex.org/I4179309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082788397"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.5188,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6908827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1454","last_page":"1459"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9847999811172485,"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":0.8700867891311646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8092201948165894},{"id":"https://openalex.org/keywords/presumption","display_name":"Presumption","score":0.5454285144805908},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4929165840148926},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.48790428042411804},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.454074501991272},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3210160434246063},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19491782784461975},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16257688403129578}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8700867891311646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8092201948165894},{"id":"https://openalex.org/C2780253743","wikidata":"https://www.wikidata.org/wiki/Q132382","display_name":"Presumption","level":2,"score":0.5454285144805908},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4929165840148926},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.48790428042411804},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.454074501991272},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3210160434246063},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19491782784461975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16257688403129578},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit54713.2023.10206444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit54713.2023.10206444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-129990","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-129990","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1501823362","https://openalex.org/W1510812122","https://openalex.org/W2168405694","https://openalex.org/W2950808099","https://openalex.org/W2950929549","https://openalex.org/W2950963126","https://openalex.org/W3005066471","https://openalex.org/W3080587002","https://openalex.org/W3080710500","https://openalex.org/W3093548068","https://openalex.org/W3130878888","https://openalex.org/W3174647784","https://openalex.org/W3203472452","https://openalex.org/W3207912101","https://openalex.org/W3208202329","https://openalex.org/W3209818426","https://openalex.org/W4206530644","https://openalex.org/W4214717370","https://openalex.org/W4283800968","https://openalex.org/W4318619660","https://openalex.org/W4382449430","https://openalex.org/W4386066409","https://openalex.org/W6630117878","https://openalex.org/W6630683246","https://openalex.org/W6728757088","https://openalex.org/W6754151078","https://openalex.org/W6762518091","https://openalex.org/W6773427235","https://openalex.org/W6782072688","https://openalex.org/W6784774785","https://openalex.org/W6802433127","https://openalex.org/W6802929464","https://openalex.org/W6803104733","https://openalex.org/W6841348440"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W4287753704","https://openalex.org/W3036260055","https://openalex.org/W3158925485","https://openalex.org/W2996735312"],"abstract_inverted_index":{"Most":[0],"existing":[1],"federated":[2],"multi-armed":[3],"bandits":[4],"(FMAB)":[5],"designs":[6],"are":[7,121,141,148],"based":[8],"on":[9,44,117],"the":[10,16,22,34,62,65,78,125,133],"presumption":[11],"that":[12,160],"clients":[13,45,66,135],"will":[14],"implement":[15],"new":[17],"design":[18],"to":[19,32,150],"collaborate":[20],"with":[21,136],"server.":[23],"In":[24],"reality,":[25],"however,":[26],"it":[27],"may":[28],"not":[29],"be":[30],"possible":[31],"modify":[33],"client":[35,164],"protocols.":[36],"Motivated":[37],"by":[38],"this":[39,41,76],"limitation,":[40],"work":[42],"focuses":[43],"who":[46],"always":[47],"maximize":[48],"their":[49,152],"individual":[50],"cumulative":[51],"rewards,":[52],"and":[53,88,95,107,119],"introduces":[54],"a":[55,180],"novel":[56,98,145],"idea":[57],"of":[58,85,115],"reward":[59,73],"teaching,":[60,90],"where":[61,144],"server":[63,79],"guides":[64],"towards":[67],"global":[68],"optimality":[69],"through":[70],"implicit":[71],"local":[72],"adjustments.":[74],"Under":[75],"framework,":[77],"faces":[80],"two":[81],"tightly":[82],"coupled":[83],"tasks":[84],"bandit":[86],"learning":[87],"target":[89],"whose":[91],"combination":[92],"is":[93,103,177],"non-trivial":[94],"challenging.":[96],"A":[97],"algorithm,":[99],"called":[100],"Teaching-After-Learning":[101],"(TAL),":[102],"proposed,":[104],"which":[105,176],"encourages":[106],"discourages":[108],"clients\u2019":[109,126],"explorations":[110],"separately.":[111],"General":[112],"performance":[113],"analyses":[114],"TAL":[116,166],"regret":[118],"cost":[120],"first":[122],"established":[123],"when":[124,161],"strategies":[127,140],"satisfy":[128],"certain":[129],"requirements.":[130],"To":[131],"particularize":[132],"results,":[134],"UCB":[137],"or":[138],"\u03b5-greedy":[139],"then":[142],"considered,":[143],"technical":[146],"approaches":[147],"developed":[149],"analyze":[151],"warm-start":[153],"behaviors.":[154],"The":[155],"obtained":[156],"guarantees":[157],"concretely":[158],"demonstrate":[159],"facing":[162],"these":[163],"strategies,":[165],"achieves":[167],"logarithmic":[168,173],"regrets":[169],"while":[170],"only":[171],"incurring":[172],"adjustment":[174],"costs,":[175],"order-optimal":[178],"w.r.t.":[179],"natural":[181],"lower":[182],"bound.":[183]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}