{"id":"https://openalex.org/W3186202482","doi":"https://doi.org/10.23919/acc50511.2021.9483345","title":"Batched Learning in Generalized Linear Contextual Bandits with General Decision Sets","display_name":"Batched Learning in Generalized Linear Contextual Bandits with General Decision Sets","publication_year":2021,"publication_date":"2021-05-25","ids":{"openalex":"https://openalex.org/W3186202482","doi":"https://doi.org/10.23919/acc50511.2021.9483345","mag":"3186202482"},"language":"en","primary_location":{"id":"doi:10.23919/acc50511.2021.9483345","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","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/A5016243877","display_name":"Zhimei Ren","orcid":"https://orcid.org/0000-0002-2872-5842"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhimei Ren","raw_affiliation_strings":["Stanford University,Department of Statistics,Stanford,CA,USA,94305"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Statistics,Stanford,CA,USA,94305","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088606320","display_name":"Zhengyuan Zhou","orcid":"https://orcid.org/0000-0002-0005-9411"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengyuan Zhou","raw_affiliation_strings":["School of Business, New York University,NY,USA,10003"],"affiliations":[{"raw_affiliation_string":"School of Business, New York University,NY,USA,10003","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057936833","display_name":"Jayant Kalagnanam","orcid":"https://orcid.org/0009-0009-5051-2606"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayant R. Kalagnanam","raw_affiliation_strings":["IBM Research,Yorktown Heights,NY,USA,10598"],"affiliations":[{"raw_affiliation_string":"IBM Research,Yorktown Heights,NY,USA,10598","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016243877"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.5228,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68169173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4958","last_page":"4963"},"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":0.9891999959945679,"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":0.9736999869346619,"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":0.8745147585868835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6970378756523132},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.6003007292747498},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5654484629631042},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.488221675157547},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4543241560459137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44503581523895264},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4357191026210785},{"id":"https://openalex.org/keywords/martingale","display_name":"Martingale (probability theory)","score":0.4350910186767578},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43377721309661865},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.42129021883010864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2465820610523224},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.177080899477005},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.0806412398815155}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8745147585868835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970378756523132},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.6003007292747498},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5654484629631042},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.488221675157547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4543241560459137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44503581523895264},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4357191026210785},{"id":"https://openalex.org/C48406656","wikidata":"https://www.wikidata.org/wiki/Q534112","display_name":"Martingale (probability theory)","level":2,"score":0.4350910186767578},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43377721309661865},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.42129021883010864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2465820610523224},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.177080899477005},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0806412398815155},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc50511.2021.9483345","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1487320471","https://openalex.org/W1687714866","https://openalex.org/W1720450983","https://openalex.org/W1809653203","https://openalex.org/W1835900096","https://openalex.org/W1958090791","https://openalex.org/W1998498767","https://openalex.org/W2021866613","https://openalex.org/W2049934117","https://openalex.org/W2061753713","https://openalex.org/W2069129115","https://openalex.org/W2097360283","https://openalex.org/W2103959887","https://openalex.org/W2106554316","https://openalex.org/W2112420033","https://openalex.org/W2160163723","https://openalex.org/W2163590988","https://openalex.org/W2166253248","https://openalex.org/W2271491060","https://openalex.org/W2592998600","https://openalex.org/W2620289825","https://openalex.org/W2621143418","https://openalex.org/W2773557179","https://openalex.org/W2785875001","https://openalex.org/W2793124255","https://openalex.org/W2914156981","https://openalex.org/W2928820257","https://openalex.org/W2950929549","https://openalex.org/W2962736281","https://openalex.org/W2962901934","https://openalex.org/W2963661728","https://openalex.org/W2963695335","https://openalex.org/W2963860006","https://openalex.org/W2964297722","https://openalex.org/W2985924367","https://openalex.org/W3017342111","https://openalex.org/W3034687036","https://openalex.org/W3044872185","https://openalex.org/W3121632328","https://openalex.org/W3124121179","https://openalex.org/W4206275166","https://openalex.org/W4214481829","https://openalex.org/W4294541781","https://openalex.org/W4299286629","https://openalex.org/W4301281798","https://openalex.org/W6629353124","https://openalex.org/W6633965395","https://openalex.org/W6638427827","https://openalex.org/W6683757025","https://openalex.org/W6684381734","https://openalex.org/W6684588631","https://openalex.org/W6694675824","https://openalex.org/W6734301959","https://openalex.org/W6738526744","https://openalex.org/W6738737708","https://openalex.org/W6747694793","https://openalex.org/W6760976760","https://openalex.org/W6806471512"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W4385742498","https://openalex.org/W3041944716","https://openalex.org/W2901492934","https://openalex.org/W4386715814","https://openalex.org/W2952181314","https://openalex.org/W3207447243","https://openalex.org/W3144950473"],"abstract_inverted_index":{"In":[0,55],"real-world":[1],"adaptive":[2],"personalized":[3],"decision":[4,13,72,173],"making,":[5],"due":[6],"to":[7],"physical":[8],"and/or":[9],"resource":[10],"constraints,":[11],"a":[12,87,97,108,124,134,147],"maker":[14],"often":[15],"does":[16],"not":[17],"have":[18],"the":[19,24,27,49,60,71,84,113],"luxury":[20],"of":[21,62,86,90,116],"immediately":[22],"incorporating":[23],"feedback":[25,82],"from":[26,48,103],"previous":[28],"individual":[29],"into":[30,150],"forming":[31],"new":[32],"policies":[33],"for":[34],"future":[35],"individuals.":[36],"This":[37],"is":[38],"an":[39],"important":[40],"aspect":[41],"that":[42,111],"has":[43],"largely":[44],"been":[45],"abstracted":[46],"away":[47],"traditional":[50,76],"online":[51,77],"learning/decision":[52],"making":[53,174],"literature.":[54],"this":[56,119,141],"paper,":[57],"we":[58],"study":[59],"problem":[61],"batched":[63,126],"learning":[64,127],"in":[65,75,118,175],"generalized":[66,151],"linear":[67,152],"contextual":[68,153],"bandits":[69,154,162],"where":[70],"maker,":[73],"unlike":[74],"learning,":[78],"can":[79,99],"only":[80,100],"access":[81],"at":[83],"end":[85],"limited":[88],"number":[89],"batches,":[91],"and":[92,121,167],"when":[93],"selecting":[94],"actions":[95],"within":[96],"batch,":[98],"use":[101],"information":[102],"prior":[104],"batches.":[105],"We":[106],"provide":[107,146],"lower":[109,142],"bound":[110],"characterizes":[112],"fundamental":[114],"limit":[115],"performance":[117],"setting":[120,163],"then":[122],"give":[123],"DCB-based":[125],"algorithm":[128],"whose":[129],"regret":[130],"bound,":[131],"obtained":[132],"using":[133],"self-normalized":[135],"martingale":[136],"style":[137],"analysis,":[138],"nearly":[139],"matches":[140],"bound.":[143],"Our":[144],"results":[145],"novel":[148],"inquiry":[149],"with":[155],"arbitrary":[156],"action":[157],"sets,":[158],"which":[159],"include":[160],"several":[161],"as":[164],"special":[165],"cases":[166],"thus":[168],"shed":[169],"light":[170],"on":[171],"batch-constrained":[172],"general.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}