{"id":"https://openalex.org/W7208770282","doi":"https://doi.org/10.48550/arxiv.2609.03870","title":"Data-Driven Brownian Reflection Control","display_name":"Data-Driven Brownian Reflection Control","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208770282","doi":"https://doi.org/10.48550/arxiv.2609.03870"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.03870","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03870","pdf_url":"https://arxiv.org/pdf/2609.03870","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.03870","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064855799","display_name":"Guodong Pang","orcid":"https://orcid.org/0000-0001-6468-0429","observed_orcids":["https://orcid.org/0000-0001-6468-0429"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Pang, Guodong","raw_affiliation_strings":["Department of Computational Applied Mathematics and Operations Research , George R. Brown School of En- gineering , Rice University , Houston , TX 77005 ;","School of Mathematical Sciences , University of Chinese Academy of Sciences , Beijing , 100049 , China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Applied Mathematics and Operations Research , George R. Brown School of En- gineering , Rice University , Houston , TX 77005 ;","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"School of Mathematical Sciences , University of Chinese Academy of Sciences , Beijing , 100049 , China;","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053767105","display_name":"Dacheng Yao","orcid":"https://orcid.org/0000-0001-5893-5595","observed_orcids":["https://orcid.org/0000-0001-5893-5595"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao, Dacheng","raw_affiliation_strings":["School of Mathematical Sciences , University of Chinese Academy of Sciences , Beijing , 100049 , China;","State Key Laboratory of Mathematical Sciences , Academy of Mathematics and Systems Science , Chinese Academy of Sciences , Beijing , 100190 , China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences , University of Chinese Academy of Sciences , Beijing , 100049 , China;","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Mathematical Sciences , Academy of Mathematics and Systems Science , Chinese Academy of Sciences , Beijing , 100190 , China;","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5149978076","display_name":"Hao Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin, Hao","raw_affiliation_strings":["Academy of Mathematics and Systems Science , Chinese Academy of Sciences , Beijing , 100190 , China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Mathematics and Systems Science , Chinese Academy of Sciences , Beijing , 100190 , China;","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.7954000234603882,"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":0.7954000234603882,"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/T10067","display_name":"Stochastic processes and financial applications","score":0.12110000103712082,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.044599998742341995,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-driven-control","display_name":"data-driven control","score":0.7419999837875366},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.800000011920929},{"id":"https://openalex.org/keywords/nonstationarity","display_name":"non-stationarity","score":0.8899999856948853},{"id":"https://openalex.org/keywords/reflected-brownian-motion","display_name":"reflected Brownian motion","score":0.7239999771118164},{"id":"https://openalex.org/keywords/moving-boundary","display_name":"moving boundary","score":0.5320000052452087},{"id":"https://openalex.org/keywords/estimator-consistency","display_name":"estimator consistency","score":0.5910000205039978},{"id":"https://openalex.org/keywords/mean-squared-error-bounds","display_name":"mean squared error bounds","score":0.671999990940094}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7197999954223633},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C112401455","wikidata":"https://www.wikidata.org/wiki/Q178036","display_name":"Brownian motion","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C75438885","wikidata":"https://www.wikidata.org/wiki/Q3403615","display_name":"Large deviations theory","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.03870","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03870","pdf_url":"https://arxiv.org/pdf/2609.03870","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,"listed_in":[],"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":"doi:10.48550/arxiv.2609.03870","doi":"https://doi.org/10.48550/arxiv.2609.03870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.03870","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.03870","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03870","pdf_url":"https://arxiv.org/pdf/2609.03870","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208770282.pdf","grobid_xml":"https://content.openalex.org/works/W7208770282.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4389650722","https://openalex.org/W4403888236","https://openalex.org/W4405486670","https://openalex.org/W7101392274"],"related_works":["https://openalex.org/W4403403535","https://openalex.org/W4403888236","https://openalex.org/W4389650722","https://openalex.org/W2009534880","https://openalex.org/W7116158052","https://openalex.org/W4402921774","https://openalex.org/W4402627664","https://openalex.org/W4414296755","https://openalex.org/W3159836063","https://openalex.org/W3151642287"],"abstract_inverted_index":{"We":[0,16,48],"study":[1],"a":[2,8,19,124],"data-driven":[3],"reflection":[4,166],"control":[5,156],"problem":[6],"for":[7,127,152,184],"Brownian":[9,134],"model":[10],"with":[11,146,193],"unknown":[12],"drift":[13],"and":[14,37,55,64,94,148,164],"volatility.":[15],"first":[17],"propose":[18,50],"learn-then-optimize":[20],"(LTO)":[21],"algorithm:":[22],"it":[23],"estimates":[24],"the":[25,31,34,39,62,104,108,115,131,153,157,162,172,175,185],"policy-relevant":[26],"parameter":[27],"during":[28],"exploration,":[29,92],"plugs":[30],"estimate":[32],"into":[33,91],"optimality":[35],"equation,":[36],"exploits":[38],"resulting":[40],"policy---achieving":[41],"an":[42,68],"$O(\\sqrt{T})$":[43],"finite-time":[44],"expected":[45],"regret":[46,72,90,98],"bound.":[47,73],"further":[49,121],"two":[51],"algorithms,":[52],"adaptive-updating":[53,57],"(AU)":[54],"full-history":[56],"(AU-FH),":[58],"which":[59,118,155],"continuously":[60],"update":[61],"estimator":[63],"reflecting":[65],"level,":[66],"attaining":[67],"improved":[69],"$O(\\log":[70],"T)$":[71],"Notably,":[74],"AU-FH":[75],"algorithms":[76],"leverages":[77],"all":[78],"historical":[79],"data,":[80],"yielding":[81],"better":[82],"performance":[83],"in":[84],"numerical":[85],"simulations.":[86],"Our":[87],"analysis":[88],"decomposes":[89],"transient,":[93],"learning":[95,138],"components.":[96],"Transient":[97],"from":[99,111],"nonstationarity":[100],"is":[101],"bounded":[102,122],"by":[103],"time-integrated":[105],"deviation":[106],"of":[107,130,174],"transition":[109],"semigroup":[110],"stationarity":[112],"evaluated":[113],"on":[114],"holding":[116],"cost,":[117],"can":[119],"be":[120],"via":[123,190],"Foster-Lyapunov":[125],"inequality":[126],"exponential":[128],"convergence":[129],"controlled":[132],"reflected":[133],"motion":[135],"(RBM).":[136],"For":[137],"regret,":[139],"we":[140,170],"establish":[141],"local":[142],"regularity":[143],"properties":[144],"together":[145],"consistency":[147],"mean-squared":[149],"error":[150],"bounds":[151,183],"estimator,":[154],"stationary":[158],"cost":[159],"gap":[160],"between":[161],"learned":[163],"optimal":[165],"policies.":[167],"In":[168],"addition,":[169],"leverage":[171],"monotonicity":[173],"moving":[176],"boundary":[177],"Skorokhod":[178],"map":[179],"to":[180],"derive":[181],"moment":[182],"AU":[186],"algorithms'":[187],"switching":[188],"states,":[189],"pathwise":[191],"comparison":[192],"fixed-boundary":[194],"RBMs.":[195]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-05T00:00:00"}