{"id":"https://openalex.org/W7160919662","doi":"https://doi.org/10.48550/arxiv.2605.10289","title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","display_name":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160919662","doi":"https://doi.org/10.48550/arxiv.2605.10289"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.10289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135990069","display_name":"Bochao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bochao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135975301","display_name":"Yao Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135916355","display_name":"Wei Chen","orcid":"https://orcid.org/0009-0005-1124-8217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135980147","display_name":"Fang Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9886000156402588,"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":0.9886000156402588,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.0020000000949949026,"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":0.6639000177383423},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.646399974822998},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.6216999888420105},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.47380000352859497},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.46399998664855957},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.44670000672340393},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.3889000117778778},{"id":"https://openalex.org/keywords/online-algorithm","display_name":"Online algorithm","score":0.3846000134944916}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6639000177383423},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.646399974822998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.633899986743927},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.6216999888420105},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.47380000352859497},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44670000672340393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42260000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.3889000117778778},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C18483071","wikidata":"https://www.wikidata.org/wiki/Q168432","display_name":"Anchoring","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7952567338943481}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline-to-online":[0],"learning":[1,65],"aims":[2],"to":[3,32,63,81,86,102,172,195],"improve":[4],"online":[5,25,97,135,144,197],"decision-making":[6],"by":[7,154,157],"leveraging":[8],"offline":[9,23,35,170,193,211],"logged":[10],"data.":[11],"A":[12],"central":[13],"challenge":[14],"in":[15,76],"this":[16,110],"setting":[17],"is":[18,180],"the":[19,87,127,131,143,178,188,202,208,214],"distribution":[20,155,205],"shift":[21,156,179,206],"between":[22],"and":[24,60,98,104,142,163,199,207],"environments.":[26],"While":[27],"some":[28],"existing":[29],"works":[30],"attempt":[31],"leverage":[33],"shifted":[34],"data,":[36],"they":[37],"largely":[38],"rely":[39],"on":[40],"UCB-type":[41],"algorithms.":[42],"Thompson":[43],"sampling":[44],"(TS)":[45],"represents":[46],"another":[47],"canonical":[48],"class":[49],"of":[50,133,204,210,223],"bandit":[51],"algorithms,":[52],"well":[53],"known":[54],"for":[55,160,165],"its":[56,67],"strong":[57],"empirical":[58],"performance":[59],"naturally":[61],"suited":[62],"offline-to-online":[64],"through":[66],"Bayesian":[68],"formulation.":[69],"However,":[70],"unlike":[71],"UCB":[72],"indices,":[73],"posterior":[74,136,140],"samples":[75],"TS":[77,116],"are":[78],"not":[79],"guaranteed":[80],"be":[82],"optimistic":[83],"with":[84],"respect":[85],"true":[88],"arm":[89,128],"means.":[90],"This":[91],"makes":[92],"indices":[93],"constructed":[94],"from":[95],"purely":[96],"hybrid":[99,139],"data":[100,194,212],"difficult":[101],"compare":[103],"complicates":[105],"their":[106],"use.":[107],"To":[108],"address":[109],"issue,":[111],"we":[112],"propose":[113],"sample-mean":[114],"anchored":[115],"(Anchor-TS),":[117],"which":[118],"introduces":[119],"a":[120,138],"novel":[121],"median-based":[122],"anchoring":[123,149],"rule":[124],"that":[125,187],"defines":[126],"index":[129],"as":[130],"median":[132,148],"an":[134],"sample,":[137,141],"sample":[145],"mean.":[146],"The":[147],"systematically":[150],"corrects":[151],"bias":[152],"induced":[153],"mitigating":[158],"over-estimation":[159],"suboptimal":[161],"arms":[162],"under-estimation":[164],"optimal":[166],"arms,":[167],"while":[168],"exploiting":[169],"information":[171],"obtain":[173],"more":[174],"accurate":[175],"estimates":[176],"when":[177],"small.":[181],"We":[182],"establish":[183],"theoretical":[184],"guarantees":[185],"showing":[186],"proposed":[189],"algorithm":[190,225],"safely":[191],"leverages":[192],"accelerate":[196],"learning,":[198],"quantifying":[200],"how":[201],"degree":[203],"size":[209],"affect":[213],"resulting":[215],"regret":[216],"reduction.":[217],"Extensive":[218],"experiments":[219],"demonstrate":[220],"consistent":[221],"improvements":[222],"our":[224],"over":[226],"baselines.":[227]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}