{"id":"https://openalex.org/W7092779238","doi":"https://doi.org/10.1109/isit63088.2025.11195415","title":"Refined PAC-Bayes Bounds for Offline Bandits","display_name":"Refined PAC-Bayes Bounds for Offline Bandits","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W7092779238","doi":"https://doi.org/10.1109/isit63088.2025.11195415"},"language":null,"primary_location":{"id":"doi:10.1109/isit63088.2025.11195415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit63088.2025.11195415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":null,"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),Stockholm"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE),Stockholm","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tobias J. Oechtering","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":false,"raw_author_name":"Tobias J. Oechtering","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE),Stockholm"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE),Stockholm","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mikael Skoglund","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":false,"raw_author_name":"Mikael Skoglund","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE),Stockholm"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE),Stockholm","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60519126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9840999841690063,"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":0.9840999841690063,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.005900000222027302,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0010000000474974513,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6087999939918518},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.5742999911308289},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5554999709129333},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4011000096797943},{"id":"https://openalex.org/keywords/parameter-space","display_name":"Parameter space","score":0.30250000953674316},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.2872999906539917}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6087999939918518},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5685999989509583},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5299999713897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4320000112056732},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit63088.2025.11195415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit63088.2025.11195415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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","display_name":"Reduced inequalities","score":0.4091566801071167}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1503090374","https://openalex.org/W1628829797","https://openalex.org/W1999678910","https://openalex.org/W2014384147","https://openalex.org/W2029029543","https://openalex.org/W2094062207","https://openalex.org/W2103012681","https://openalex.org/W2116942894","https://openalex.org/W2251567929","https://openalex.org/W3083184774","https://openalex.org/W3197262663","https://openalex.org/W4211030719","https://openalex.org/W4212934686","https://openalex.org/W4236362309","https://openalex.org/W4243316134","https://openalex.org/W4385976190"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"refined":[5],"probabilistic":[6],"bounds":[7,23,84],"on":[8,20,28,44,70,77],"empirical":[9],"reward":[10],"estimates":[11],"for":[12],"off-policy":[13],"learning":[14],"in":[15],"bandit":[16],"problems.":[17],"We":[18,62,80],"build":[19],"the":[21,48,55,74,91,100,105,108],"PAC-Bayesian":[22],"from":[24],"[1]\u2013[4]":[25],"and":[26,73],"improve":[27],"their":[29],"results":[30],"using":[31],"a":[32,45],"new":[33],"parameter":[34,103],"optimization":[35],"approach":[36],"introduced":[37],"by":[38,98],"[5].":[39],"This":[40],"technique":[41],"is":[42],"based":[43,69,76],"discretization":[46],"of":[47,50,107],"space":[49],"possible":[51],"events":[52],"to":[53],"optimize":[54],"\u201cin":[56,101],"probability\u201d":[57,102],"parameter,":[58],"<tex":[59],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[60,110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\lambda$</tex>.":[61],"provide":[63],"two":[64],"parameter-free":[65],"PAC-Bayes":[66],"bounds,":[67],"one":[68],"Hoeffding-Azuma's":[71],"inequality":[72],"other":[75],"Bernstein's":[78],"inequality.":[79],"prove":[81],"that":[82],"our":[83],"are":[85],"almost":[86],"optimal":[87],"as":[88,94],"they":[89],"recover":[90],"same":[92],"rate":[93],"would":[95],"be":[96],"obtained":[97],"setting":[99],"after":[104],"realization":[106],"data.<sup":[109],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[111]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-21T00:00:00"}