{"id":"https://openalex.org/W4400351197","doi":"https://doi.org/10.1109/smartnets61466.2024.10577740","title":"Provably Correct SGD-Based Exploration for Generalized Stochastic Bandit Problem","display_name":"Provably Correct SGD-Based Exploration for Generalized Stochastic Bandit Problem","publication_year":2024,"publication_date":"2024-05-28","ids":{"openalex":"https://openalex.org/W4400351197","doi":"https://doi.org/10.1109/smartnets61466.2024.10577740"},"language":"en","primary_location":{"id":"doi:10.1109/smartnets61466.2024.10577740","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smartnets61466.2024.10577740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Smart Applications, Communications and Networking (SmartNets)","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/A5104049478","display_name":"Jialin Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jialin Dong","raw_affiliation_strings":["University of California,Los Angeles,CA,US,90095"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles,CA,US,90095","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118983749","display_name":"Jiayi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Wang","raw_affiliation_strings":["The University of Utah,Salt Lake City,UT,US,84112"],"affiliations":[{"raw_affiliation_string":"The University of Utah,Salt Lake City,UT,US,84112","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072096775","display_name":"Lin F. Yang","orcid":"https://orcid.org/0000-0003-4602-3366"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin F. Yang","raw_affiliation_strings":["University of California,Los Angeles,CA,US,90095"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles,CA,US,90095","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104049478"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11802034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9947999715805054,"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":0.9947999715805054,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.9853000044822693,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9693999886512756,"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/computer-science","display_name":"Computer science","score":0.65557461977005},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4933284819126129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4090280830860138},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24416056275367737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65557461977005},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4933284819126129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090280830860138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24416056275367737}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smartnets61466.2024.10577740","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smartnets61466.2024.10577740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Smart Applications, Communications and Networking (SmartNets)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1570963478","https://openalex.org/W2025356004","https://openalex.org/W2086161653","https://openalex.org/W2119738618","https://openalex.org/W2163840227","https://openalex.org/W2168405694","https://openalex.org/W2621143418","https://openalex.org/W2963520461","https://openalex.org/W3010248974","https://openalex.org/W3038426846","https://openalex.org/W3102449016","https://openalex.org/W3157699871","https://openalex.org/W3166586424","https://openalex.org/W4206275166","https://openalex.org/W6677707158","https://openalex.org/W6678092311","https://openalex.org/W6684050718","https://openalex.org/W6734301959","https://openalex.org/W6738526744","https://openalex.org/W6779294953","https://openalex.org/W6780025039","https://openalex.org/W6796367353","https://openalex.org/W6797433551"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Bandit":[0],"problems":[1],"have":[2],"been":[3],"widely":[4],"used":[5],"in":[6,30,40,53,82,212],"wireless":[7,54],"communication":[8],"systems":[9],"which":[10,49,66,118],"involve":[11],"generalized":[12],"reward":[13,127],"models":[14,48],"and":[15,139,197],"may":[16,67],"suffer":[17],"high":[18,113],"computational":[19,35],"complexity.":[20],"Despite":[21],"the":[22,62,83,94,144,147,169,192,202,221],"success":[23],"of":[24,157,171,194,204,223],"applying":[25],"stochastic":[26,31,122],"gradient":[27],"descent":[28],"(SGD)":[29],"bandits":[32,123],"to":[33,86,121,134,219],"reduce":[34],"complexity,":[36],"several":[37],"limitations":[38],"persist":[39],"state-of-the-art.":[41],"Specifically,":[42],"current":[43,148],"papers":[44],"only":[45,59],"consider":[46],"linear":[47],"is":[50,201],"not":[51,68],"practical":[52],"communication.":[55],"Their":[56],"algorithms":[57],"are":[58,74],"guaranteed":[60],"by":[61],"expected":[63],"regret":[64,115,170,210],"bound,":[65],"be":[69],"effective":[70],"when":[71],"many":[72],"actions":[73,138],"sub-optimal.":[75],"Additionally,":[76],"existing":[77,208],"SGD-based":[78,109],"approaches":[79],"raise":[80],"bias":[81],"estimation":[84,156],"due":[85],"a":[87,112],"greedy":[88],"action":[89,145,149],"selection":[90],"strategy,":[91],"deviating":[92],"from":[93,146],"conventional":[95],"SGD":[96],"approach":[97],"that":[98,163],"uniformly":[99,140],"samples.":[100],"To":[101],"address":[102],"these":[103],"limitations,":[104],"we":[105,161],"propose":[106],"an":[107,131,154],"online":[108],"algorithm":[110,166],"with":[111,124,180],"probability":[114,181],"bound":[116],"guarantee,":[117],"can":[119,167],"apply":[120],"general":[125],"parametric":[126],"functions.":[128],"We":[129,215],"develop":[130],"action-elimination":[132],"strategy":[133,152],"gradually":[135],"eliminate":[136],"sub-optimal":[137],"at":[141,182],"random":[142],"select":[143],"subset.":[150],"This":[151],"guarantees":[153],"unbiased":[155],"model":[158,205],"parameters.":[159],"Theoretically,":[160],"prove":[162],"our":[164,224],"proposed":[165],"achieve":[168],"<tex":[172,184,188,198],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[173,185,189,199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$O(d":[174],"\\sqrt{n":[175],"\\log":[176],"(n":[177],"/":[178],"\\delta)})$</tex>":[179],"least":[183],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1-\\delta$</tex>,":[186],"where":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$n$</tex>":[190],"is\u2018":[191],"number\u2019":[193],"time":[195],"steps":[196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$d$</tex>":[200],"dimension":[203],"parameters,":[206],"matching":[207],"near-optimal":[209],"bounds":[211],"UCB-type":[213],"algorithms.":[214],"further":[216],"conduct":[217],"experiments":[218],"demonstrate":[220],"advantage":[222],"algorithm.":[225]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}