{"id":"https://openalex.org/W4385976190","doi":"https://doi.org/10.1109/tpami.2023.3305381","title":"PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison","display_name":"PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison","publication_year":2023,"publication_date":"2023-08-18","ids":{"openalex":"https://openalex.org/W4385976190","doi":"https://doi.org/10.1109/tpami.2023.3305381","pmid":"https://pubmed.ncbi.nlm.nih.gov/37594872"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3305381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3305381","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.16110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088006848","display_name":"Hamish Flynn","orcid":"https://orcid.org/0000-0002-4089-9087"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hamish Flynn","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102735112","display_name":"David Reeb","orcid":"https://orcid.org/0000-0002-9446-2315"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Reeb","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032539965","display_name":"Melih Kandemir","orcid":"https://orcid.org/0000-0001-6293-3656"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Melih Kandemir","raw_affiliation_strings":["Department of Mathematics and Computer Science (IMADA), University of Southern Denmark, Odense, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science (IMADA), University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems Group, Technische Universität Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, Technische Universität Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088006848"],"corresponding_institution_ids":["https://openalex.org/I889804353"],"apc_list":null,"apc_paid":null,"fwci":0.512,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68885735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"45","issue":"12","first_page":"15308","last_page":"15327"},"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":0.9991999864578247,"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":0.996399998664856,"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":0.7915728688240051},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.6907143592834473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.647911548614502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6160287261009216},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5712268948554993},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5415052175521851},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4435359239578247}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7915728688240051},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.6907143592834473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.647911548614502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6160287261009216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5712268948554993},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5415052175521851},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4435359239578247}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2023.3305381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3305381","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37594872","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37594872","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/92a89091-a8e6-433d-b724-4951b92ccf77","is_oa":true,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/92a89091-a8e6-433d-b724-4951b92ccf77","pdf_url":"https://arxiv.org/pdf/2211.16110","source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Flynn, H, Reeb, D, Kandemir, M & Peters, J 2023, 'PAC-Bayes Bounds for Bandit Problems : A Survey and Experimental Comparison', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 12, pp. 15308-15327. https://doi.org/10.1109/TPAMI.2023.3305381","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:sdu.dk:openaire_cris_publications/92a89091-a8e6-433d-b724-4951b92ccf77","is_oa":true,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/92a89091-a8e6-433d-b724-4951b92ccf77","pdf_url":"https://arxiv.org/pdf/2211.16110","source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Flynn, H, Reeb, D, Kandemir, M & Peters, J 2023, 'PAC-Bayes Bounds for Bandit Problems : A Survey and Experimental Comparison', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 12, pp. 15308-15327. https://doi.org/10.1109/TPAMI.2023.3305381","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385976190.pdf"},"referenced_works_count":171,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W64088143","https://openalex.org/W138682821","https://openalex.org/W659523800","https://openalex.org/W1499669280","https://openalex.org/W1510812122","https://openalex.org/W1521230616","https://openalex.org/W1542886316","https://openalex.org/W1564755532","https://openalex.org/W1570963478","https://openalex.org/W1594783240","https://openalex.org/W1599118604","https://openalex.org/W1607832978","https://openalex.org/W1628114069","https://openalex.org/W1754294493","https://openalex.org/W1771410628","https://openalex.org/W1835900096","https://openalex.org/W1859987214","https://openalex.org/W1907483012","https://openalex.org/W1998427280","https://openalex.org/W1998498767","https://openalex.org/W1999376700","https://openalex.org/W1999678910","https://openalex.org/W2014384147","https://openalex.org/W2056921512","https://openalex.org/W2062714872","https://openalex.org/W2077902449","https://openalex.org/W2086206379","https://openalex.org/W2087347434","https://openalex.org/W2089657469","https://openalex.org/W2098258765","https://openalex.org/W2103715332","https://openalex.org/W2107074784","https://openalex.org/W2107726111","https://openalex.org/W2108005930","https://openalex.org/W2108114251","https://openalex.org/W2108810117","https://openalex.org/W2112065930","https://openalex.org/W2115065944","https://openalex.org/W2116942894","https://openalex.org/W2119240219","https://openalex.org/W2119611763","https://openalex.org/W2119850747","https://openalex.org/W2121358800","https://openalex.org/W2122899522","https://openalex.org/W2130464645","https://openalex.org/W2130801532","https://openalex.org/W2132862423","https://openalex.org/W2135194391","https://openalex.org/W2146807381","https://openalex.org/W2149991487","https://openalex.org/W2158388185","https://openalex.org/W2168022998","https://openalex.org/W2168405694","https://openalex.org/W2225156818","https://openalex.org/W2238973924","https://openalex.org/W2466856990","https://openalex.org/W2725896932","https://openalex.org/W2736601468","https://openalex.org/W2745933720","https://openalex.org/W2781726626","https://openalex.org/W2787642919","https://openalex.org/W2792422168","https://openalex.org/W2797937785","https://openalex.org/W2808225711","https://openalex.org/W2912811302","https://openalex.org/W2912998451","https://openalex.org/W2949561945","https://openalex.org/W2950929549","https://openalex.org/W2950942124","https://openalex.org/W2951595529","https://openalex.org/W2963252079","https://openalex.org/W2963285578","https://openalex.org/W2963319217","https://openalex.org/W2969998143","https://openalex.org/W3005896558","https://openalex.org/W3034274776","https://openalex.org/W3035443457","https://openalex.org/W3044132587","https://openalex.org/W3098679278","https://openalex.org/W3120740533","https://openalex.org/W3124121179","https://openalex.org/W3127126451","https://openalex.org/W3138939485","https://openalex.org/W3199328447","https://openalex.org/W3200935055","https://openalex.org/W3201965976","https://openalex.org/W3205218451","https://openalex.org/W3212335303","https://openalex.org/W4206275166","https://openalex.org/W4206530644","https://openalex.org/W4220868778","https://openalex.org/W4234228486","https://openalex.org/W4238893454","https://openalex.org/W4242067627","https://openalex.org/W4243316134","https://openalex.org/W4286897948","https://openalex.org/W4287123984","https://openalex.org/W4287124514","https://openalex.org/W4287755399","https://openalex.org/W4287994589","https://openalex.org/W4288115438","https://openalex.org/W4288358578","https://openalex.org/W4289362772","https://openalex.org/W4293052541","https://openalex.org/W4293433236","https://openalex.org/W4297738147","https://openalex.org/W4297813512","https://openalex.org/W4300605669","https://openalex.org/W4300971841","https://openalex.org/W4302012848","https://openalex.org/W4319653703","https://openalex.org/W6602031475","https://openalex.org/W6622131334","https://openalex.org/W6630683246","https://openalex.org/W6633472939","https://openalex.org/W6635508374","https://openalex.org/W6635963195","https://openalex.org/W6636699765","https://openalex.org/W6636705695","https://openalex.org/W6636753970","https://openalex.org/W6637264448","https://openalex.org/W6637716813","https://openalex.org/W6638018090","https://openalex.org/W6638427827","https://openalex.org/W6638836233","https://openalex.org/W6674868663","https://openalex.org/W6675604041","https://openalex.org/W6675657435","https://openalex.org/W6676352665","https://openalex.org/W6676576766","https://openalex.org/W6677100322","https://openalex.org/W6677213297","https://openalex.org/W6677888739","https://openalex.org/W6677941903","https://openalex.org/W6678113768","https://openalex.org/W6678182789","https://openalex.org/W6679257226","https://openalex.org/W6681428133","https://openalex.org/W6683372824","https://openalex.org/W6684839461","https://openalex.org/W6685562342","https://openalex.org/W6734517396","https://openalex.org/W6735544424","https://openalex.org/W6741002519","https://openalex.org/W6743268725","https://openalex.org/W6747473740","https://openalex.org/W6748284903","https://openalex.org/W6748863552","https://openalex.org/W6749700008","https://openalex.org/W6752583447","https://openalex.org/W6752717554","https://openalex.org/W6754419986","https://openalex.org/W6757689330","https://openalex.org/W6758359583","https://openalex.org/W6758779491","https://openalex.org/W6762806417","https://openalex.org/W6766756864","https://openalex.org/W6767142064","https://openalex.org/W6767654614","https://openalex.org/W6773539357","https://openalex.org/W6773756054","https://openalex.org/W6779864866","https://openalex.org/W6780249745","https://openalex.org/W6792120457","https://openalex.org/W6794385137","https://openalex.org/W6796663145","https://openalex.org/W6797189378","https://openalex.org/W6802995403","https://openalex.org/W6845803114","https://openalex.org/W6849682813"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W118270247"],"abstract_inverted_index":{"PAC-Bayes":[0,23,72,91],"has":[1],"recently":[2],"re-emerged":[3],"as":[4,47],"an":[5,69,78],"effective":[6],"theory":[7],"with":[8,16,57,102,122],"which":[9,30],"one":[10,86],"can":[11,44],"derive":[12],"principled":[13,55],"learning":[14],"algorithms":[15,56,101,138],"tight":[17],"performance":[18,59,103,128],"guarantees.":[19,104,129],"However,":[20],"applications":[21],"of":[22,52,71,81],"to":[24,116],"bandit":[25,48,75,100,112,137,158],"problems":[26,37,76],"are":[27,93],"relatively":[28],"rare,":[29],"is":[31],"a":[32,94,108],"great":[33],"misfortune.":[34],"Many":[35],"decision-making":[36],"in":[38],"healthcare,":[39],"finance":[40],"and":[41,77,126],"natural":[42],"sciences":[43],"be":[45,62],"modelled":[46],"problems.":[49],"In":[50,105],"many":[51],"these":[53,82],"applications,":[54],"strong":[58],"guarantees":[60],"would":[61],"very":[63],"much":[64],"appreciated.":[65],"This":[66],"survey":[67],"provides":[68],"overview":[70],"bounds":[73,92],"for":[74,97,153],"experimental":[79],"comparison":[80],"bounds.":[83,146],"On":[84,130],"the":[85,131,134],"hand,":[87,133],"we":[88,140],"found":[89],"that":[90,139],"useful":[95],"tool":[96],"designing":[98],"offline":[99,110],"our":[106],"experiments,":[107],"PAC-Bayesian":[109,135,157],"contextual":[111],"algorithm":[113],"was":[114],"able":[115],"learn":[117],"randomised":[118],"neural":[119],"network":[120],"polices":[121],"competitive":[123],"expected":[124],"reward":[125],"non-vacuous":[127],"other":[132],"online":[136],"tested":[141],"had":[142],"loose":[143],"cumulative":[144],"regret":[145],"We":[147],"conclude":[148],"by":[149],"discussing":[150],"some":[151],"topics":[152],"future":[154],"work":[155],"on":[156],"algorithms.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2025-10-10T00:00:00"}