{"id":"https://openalex.org/W4386075250","doi":"https://doi.org/10.1109/isit54713.2023.10206792","title":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","display_name":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","publication_year":2023,"publication_date":"2023-06-25","ids":{"openalex":"https://openalex.org/W4386075250","doi":"https://doi.org/10.1109/isit54713.2023.10206792"},"language":"en","primary_location":{"id":"doi:10.1109/isit54713.2023.10206792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit54713.2023.10206792","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/A5010481265","display_name":"Amaury Gouverneur","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Amaury Gouverneur","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041149980","display_name":"Borja Rodr\u00edguez-G\u00e1lvez","orcid":"https://orcid.org/0000-0002-0862-1333"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Borja Rodr\u00edguez-G\u00e1lvez","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079492269","display_name":"Tobias J. Oechtering","orcid":"https://orcid.org/0000-0002-0036-9049"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tobias J. Oechtering","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041348422","display_name":"Mikael Skoglund","orcid":"https://orcid.org/0000-0002-7926-5081"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mikael Skoglund","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010481265"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.2545,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58177618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1306","last_page":"1311"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9890000224113464,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9850999712944031,"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":0.9450037479400635},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.8891216516494751},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.788121223449707},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.7571187615394592},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5925570130348206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5737975835800171},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5027327537536621},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3794942796230316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3683393597602844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3249048590660095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21755322813987732}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9450037479400635},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.8891216516494751},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.788121223449707},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.7571187615394592},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5925570130348206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5737975835800171},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5027327537536621},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3794942796230316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3683393597602844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3249048590660095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21755322813987732},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit54713.2023.10206792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit54713.2023.10206792","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.550000011920929,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1487320471","https://openalex.org/W1496462336","https://openalex.org/W2004971231","https://openalex.org/W2021801581","https://openalex.org/W2039522160","https://openalex.org/W2057050711","https://openalex.org/W2065398693","https://openalex.org/W2103012681","https://openalex.org/W2103715332","https://openalex.org/W2106164082","https://openalex.org/W2108738385","https://openalex.org/W2118980425","https://openalex.org/W2119850747","https://openalex.org/W2141514451","https://openalex.org/W2148224612","https://openalex.org/W2158125716","https://openalex.org/W2257317309","https://openalex.org/W2787642919","https://openalex.org/W2805217655","https://openalex.org/W2962901934","https://openalex.org/W3034274776","https://openalex.org/W3083184774","https://openalex.org/W3180880273","https://openalex.org/W3202341388","https://openalex.org/W4254630254","https://openalex.org/W4281640044","https://openalex.org/W4288028699","https://openalex.org/W4308216308","https://openalex.org/W6629353124","https://openalex.org/W6633965395","https://openalex.org/W6675656252","https://openalex.org/W6675657435","https://openalex.org/W6676077707","https://openalex.org/W6677741321","https://openalex.org/W6678113768","https://openalex.org/W6681007731","https://openalex.org/W6748284903","https://openalex.org/W6751607607","https://openalex.org/W6767717172","https://openalex.org/W6773756054","https://openalex.org/W6798393534","https://openalex.org/W6838868796"],"related_works":["https://openalex.org/W3108185025","https://openalex.org/W1850547517","https://openalex.org/W2964125852","https://openalex.org/W3176022311","https://openalex.org/W4293273057","https://openalex.org/W3048056964","https://openalex.org/W4287690869","https://openalex.org/W3046298489","https://openalex.org/W3015709540","https://openalex.org/W4287816990"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,31,57,83],"study":[4],"the":[5,8,18,37,46,50,54,62,73,89],"performance":[6],"of":[7,26,49,92],"Thompson":[9,38],"Sampling":[10,39],"algorithm":[11],"for":[12,68,88],"Contextual":[13],"Bandit":[14],"problems":[15],"based":[16],"on":[17,36,45,61],"framework":[19],"introduced":[20],"by":[21],"[1]":[22,76],"and":[23,53,107],"their":[24],"concept":[25],"lifted":[27,63],"information":[28,48,64],"ratio.":[29],"First,":[30],"prove":[32],"a":[33],"comprehensive":[34],"bound":[35],"expected":[40],"cumulative":[41],"regret":[42,86],"that":[43,66],"depends":[44],"mutual":[47],"environment":[51],"parameters":[52],"history.":[55],"Then,":[56],"introduce":[58],"new":[59],"bounds":[60,87],"ratio":[65],"hold":[67],"sub-Gaussian":[69],"rewards,":[70],"thus":[71],"generalizing":[72],"results":[74],"from":[75],"which":[77],"analysis":[78],"requires":[79],"binary":[80],"rewards.":[81],"Finally,":[82],"provide":[84],"explicit":[85],"special":[90],"cases":[91],"unstructured":[93],"bounded":[94,98,108],"contextual":[95,99,110],"bandits,":[96,106],"structured":[97,104],"bandits":[100],"with":[101],"Laplace":[102],"likelihood,":[103],"Bernoulli":[105],"linear":[109],"bandits.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}