{"id":"https://openalex.org/W2997956301","doi":"https://doi.org/10.1109/isit44484.2020.9173931","title":"A Hoeffding Inequality for Finite State Markov Chains and its Applications to Markovian Bandits","display_name":"A Hoeffding Inequality for Finite State Markov Chains and its Applications to Markovian Bandits","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W2997956301","doi":"https://doi.org/10.1109/isit44484.2020.9173931","mag":"2997956301"},"language":"en","primary_location":{"id":"doi:10.1109/isit44484.2020.9173931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit44484.2020.9173931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.01199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108008397","display_name":"Vrettos Moulos","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vrettos Moulos","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Sciences,Berkeley","University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Sciences,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108008397"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0125499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2777","last_page":"2782"},"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":0.9980000257492065,"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/T12288","display_name":"Optimization and Search Problems","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/irreducibility","display_name":"Irreducibility","score":0.9047394394874573},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.674749493598938},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5991878509521484},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5753077268600464},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5751478672027588},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5688955783843994},{"id":"https://openalex.org/keywords/finite-state","display_name":"Finite state","score":0.5021557807922363},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4592871367931366},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4580170214176178},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.45428892970085144},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.45308342576026917},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.43161436915397644},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.42598554491996765},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4145027995109558},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3898577392101288},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.32895392179489136},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22131258249282837},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.11064842343330383},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06378427147865295}],"concepts":[{"id":"https://openalex.org/C2776823524","wikidata":"https://www.wikidata.org/wiki/Q6073561","display_name":"Irreducibility","level":2,"score":0.9047394394874573},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.674749493598938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5991878509521484},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5753077268600464},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5751478672027588},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5688955783843994},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.5021557807922363},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4592871367931366},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4580170214176178},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45428892970085144},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.45308342576026917},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.43161436915397644},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42598554491996765},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4145027995109558},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3898577392101288},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.32895392179489136},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22131258249282837},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.11064842343330383},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06378427147865295},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/isit44484.2020.9173931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit44484.2020.9173931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.01199","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.01199","pdf_url":"https://arxiv.org/pdf/2001.01199","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2997956301","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.01199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2001.01199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.01199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.01199","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.01199","pdf_url":"https://arxiv.org/pdf/2001.01199","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2997956301.pdf","grobid_xml":"https://content.openalex.org/works/W2997956301.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1585566614","https://openalex.org/W1586184796","https://openalex.org/W1865368880","https://openalex.org/W1972615020","https://openalex.org/W1980322272","https://openalex.org/W1982027240","https://openalex.org/W1985380836","https://openalex.org/W1998123258","https://openalex.org/W1999678910","https://openalex.org/W2001351653","https://openalex.org/W2004255137","https://openalex.org/W2009551863","https://openalex.org/W2009754940","https://openalex.org/W2021591976","https://openalex.org/W2023726000","https://openalex.org/W2036185487","https://openalex.org/W2040478633","https://openalex.org/W2049934117","https://openalex.org/W2055094761","https://openalex.org/W2056760934","https://openalex.org/W2063042357","https://openalex.org/W2082040833","https://openalex.org/W2086236043","https://openalex.org/W2089206630","https://openalex.org/W2099785391","https://openalex.org/W2103012681","https://openalex.org/W2113733815","https://openalex.org/W2125724988","https://openalex.org/W2132876566","https://openalex.org/W2147967768","https://openalex.org/W2168405694","https://openalex.org/W2785424877","https://openalex.org/W2810892111","https://openalex.org/W2950929549","https://openalex.org/W2961133442","https://openalex.org/W2963828408","https://openalex.org/W2985924367","https://openalex.org/W3101473884","https://openalex.org/W3101593467","https://openalex.org/W3102676469","https://openalex.org/W4205818646","https://openalex.org/W4206275166","https://openalex.org/W4232620022","https://openalex.org/W4233413206","https://openalex.org/W6634934147","https://openalex.org/W6680020174","https://openalex.org/W6767015913"],"related_works":["https://openalex.org/W2036185487","https://openalex.org/W2795720556","https://openalex.org/W3158007355","https://openalex.org/W3023711804","https://openalex.org/W3141562921","https://openalex.org/W2077182545","https://openalex.org/W2259964332","https://openalex.org/W1985380836","https://openalex.org/W3214209410","https://openalex.org/W2901984547","https://openalex.org/W2272256235","https://openalex.org/W2317005269","https://openalex.org/W2115679377","https://openalex.org/W3212532058","https://openalex.org/W3199492890","https://openalex.org/W3008289340","https://openalex.org/W2953130791","https://openalex.org/W2057509781","https://openalex.org/W2076430891","https://openalex.org/W2047702649"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,37,50],"Hoeffding":[4],"inequality":[5],"for":[6],"the":[7,66,96,104],"partial":[8],"sums":[9],"\u03a3":[10],"<sub":[11,18,24,28],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[12,15,19,25,29],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k=1</sub>":[13],"<sup":[14],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">n</sup>":[16],"f(X":[17],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k</sub>":[20,26],"),":[21],"where":[22],"{X":[23],"}":[27],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k\u2208Z&gt;0</sub>":[30],"is":[31,49,55,87,98],"an":[32,90],"irreducible":[33],"Markov":[34],"chain":[35],"on":[36],"finite":[38],"state":[39,67],"space":[40],"S,":[41],"and":[42,63,69],"f":[43],":":[44],"S":[45],"\u2192":[46],"[a,":[47],"b]":[48],"real-valued":[51],"function.":[52],"Our":[53],"bound":[54],"simple,":[56],"general,":[57],"since":[58],"it":[59],"only":[60],"assumes":[61],"irreducibility":[62],"finiteness":[64],"of":[65,106],"space,":[68],"powerful.":[70],"In":[71],"order":[72],"to":[73],"demonstrate":[74],"its":[75],"usefulness":[76],"we":[77],"provide":[78],"two":[79],"applications":[80],"in":[81,103],"multi-armed":[82],"bandit":[83],"problems.":[84],"The":[85],"first":[86],"about":[88],"identifying":[89],"approximately":[91],"best":[92],"Markovian":[93,107],"arm,":[94],"while":[95],"second":[97],"concerned":[99],"with":[100],"regret":[101],"minimization":[102],"context":[105],"bandits.":[108]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
