{"id":"https://openalex.org/W7166703002","doi":"https://doi.org/10.48550/arxiv.2606.28616","title":"Randomized Exploration for Linear Bandits via Absolute Perturbations","display_name":"Randomized Exploration for Linear Bandits via Absolute Perturbations","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166703002","doi":"https://doi.org/10.48550/arxiv.2606.28616"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.28616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28616","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":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.2606.28616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031877106","display_name":"Toshinori Kitamura","orcid":"https://orcid.org/0000-0002-2326-3140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kitamura, Toshinori","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103870133","display_name":"Liu S","orcid":"https://orcid.org/0000-0001-7255-0982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139634791","display_name":"Csaba Szepesv\u00e1ri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szepesv\u00e1ri, Csaba","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":0.9868000149726868,"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":0.9868000149726868,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0026000000070780516,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.0015999999595806003,"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":0.718500018119812},{"id":"https://openalex.org/keywords/frequentist-inference","display_name":"Frequentist inference","score":0.6428999900817871},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.6146000027656555},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4203000068664551},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4092999994754791},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/integrator","display_name":"Integrator","score":0.38909998536109924},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.34880000352859497},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.718500018119812},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6437000036239624},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.6428999900817871},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.6146000027656555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4092999994754791},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C79518650","wikidata":"https://www.wikidata.org/wiki/Q2081431","display_name":"Integrator","level":3,"score":0.38909998536109924},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.30070000886917114},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C31441030","wikidata":"https://www.wikidata.org/wiki/Q4291882","display_name":"Least absolute deviations","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.28616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28616","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.28616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28616","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"stochastic":[1],"linear":[2,102],"bandits,":[3],"the":[4,57,67,74,114,123,127,134,141],"canonical":[5],"Upper":[6],"Confidence":[7],"Bound":[8],"(UCB)":[9],"algorithm":[10],"admits":[11],"a":[12,45,84,157],"simple":[13,46,85],"frequentist":[14],"regret":[15,87],"analysis":[16],"but":[17],"can":[18],"be":[19],"computationally":[20,27],"demanding,":[21],"while":[22,72],"Thompson":[23,42,109],"Sampling":[24,43,110],"(TS)":[25],"is":[26],"attractive":[28],"yet":[29],"typically":[30],"harder":[31],"to":[32,35,133,156],"analyze":[33],"due":[34],"its":[36,62],"non-optimistic":[37],"nature.":[38],"We":[39,89,104],"propose":[40],"Absolute":[41,108],"(ATS),":[44],"modification":[47],"of":[48,70],"TS":[49,71,81,100],"that":[50,91,145],"ensures":[51],"optimism":[52,164],"in":[53,80,101,140,166],"expectation":[54],"by":[55,122],"replacing":[56],"signed":[58],"exploration":[59,161],"noise":[60],"with":[61,120],"absolute":[63,118],"value.":[64],"This":[65],"preserves":[66],"computational":[68],"efficiency":[69],"avoiding":[73],"technically":[75],"involved":[76],"anti-concentration":[77],"arguments":[78],"common":[79],"analyses,":[82],"enabling":[83],"UCB-style":[86],"analysis.":[88],"show":[90,144],"ATS":[92],"achieves":[93],"$\\tilde{O}(d^{3/2}\\sqrt{K})$":[94],"regret,":[95],"matching":[96],"existing":[97],"bounds":[98],"for":[99],"bandits.":[103],"further":[105],"introduce":[106],"Ensemble":[107],"(EATS),":[111],"which":[112],"takes":[113],"maximum":[115],"over":[116],"multiple":[117],"perturbations":[119],"normalization":[121],"ensemble":[124,128,147],"size.":[125],"As":[126],"size":[129],"grows,":[130],"EATS":[131],"converges":[132],"UCB":[135,138],"objective,":[136],"recovering":[137],"behavior":[139],"limit.":[142],"Experiments":[143],"moderate":[146],"sizes":[148],"already":[149],"yield":[150],"strong":[151],"performance.":[152],"Our":[153],"results":[154],"point":[155],"bridge":[158],"between":[159],"randomized":[160],"and":[162,168],"deterministic":[163],"both":[165],"theory":[167],"practice.":[169]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}