{"id":"https://openalex.org/W7154593753","doi":"https://doi.org/10.48550/arxiv.2604.13414","title":"Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence","display_name":"Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7154593753","doi":"https://doi.org/10.48550/arxiv.2604.13414"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.13414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13414","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.13414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133773818","display_name":"Ibne Farabi Shihab","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shihab, Ibne Farabi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119832027","display_name":"Sanjeda Akter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akter, Sanjeda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133750375","display_name":"Anuj Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Anuj","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133773818"],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.22759999334812164,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.22759999334812164,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.15649999678134918,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.05730000138282776,"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/minimax","display_name":"Minimax","score":0.7282000184059143},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6129999756813049},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5180000066757202},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4616999924182892},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.38989999890327454},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.38339999318122864},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.36010000109672546},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7282000184059143},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6129999756813049},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5149000287055969},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4535999894142151},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.13414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13414","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":"doi:10.48550/arxiv.2604.13414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13414","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":"article"},"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":{"Majority-vote":[0],"ensembles":[1,190],"achieve":[2,96],"variance":[3],"reduction":[4],"by":[5,127],"averaging":[6],"over":[7],"diverse,":[8],"approximately":[9],"independent":[10],"base":[11],"learners.":[12],"When":[13],"training":[14,143],"data":[15,144],"exhibits":[16],"Markov":[17,58,178],"dependence,":[18],"as":[19,210],"in":[20,35,55,86,213],"time-series":[21],"forecasting,":[22],"reinforcement":[23],"learning":[24],"(RL)":[25],"replay":[26],"buffers,":[27],"and":[28,154,187,205],"spatial":[29,181],"grids,":[30,182],"this":[31,50],"classical":[32],"guarantee":[33],"degrades":[34],"ways":[36],"that":[37,65,91],"existing":[38],"theory":[39],"does":[40],"not":[41],"fully":[42],"quantify.":[43],"We":[44,73,103],"provide":[45],"a":[46,56,70,130,151,162,168],"minimax":[47,157],"characterization":[48],"of":[49,150,173],"phenomenon":[51],"for":[52,80,196],"discrete":[53],"classification":[54,98],"fixed-dimensional":[57],"setting,":[59],"together":[60],"with":[61,122],"an":[62,76],"adaptive":[63],"algorithm":[64],"matches":[66],"the":[67,108,113,142,146,156,183,192,214],"rate":[68,158],"on":[69,107,167,176],"graph-regular":[71,169],"subclass.":[72],"first":[74],"establish":[75],"information-theoretic":[77],"lower":[78],"bound":[79],"stationary,":[81],"reversible,":[82],"geometrically":[83],"ergodic":[84],"chains":[85],"fixed":[87],"ambient":[88],"dimension,":[89],"showing":[90],"no":[92],"measurable":[93],"estimator":[94],"can":[95],"excess":[97,123],"risk":[99,124],"better":[100],"than":[101],"$\u03a9(\\sqrt{\\Tmix/n})$.":[102],"then":[104],"prove":[105],"that,":[106],"AR(1)":[109],"witness":[110],"subclass":[111],"underlying":[112],"lower-bound":[114],"construction,":[115],"dependence-agnostic":[116],"uniform":[117],"bagging":[118],"is":[119],"provably":[120],"suboptimal":[121],"bounded":[125,206],"below":[126],"$\u03a9(\\Tmix/\\sqrt{n})$,":[128],"exhibiting":[129],"$\\sqrt{\\Tmix}$":[131],"algorithmic":[132],"gap.":[133],"Finally,":[134],"we":[135],"propose":[136],"\\emph{adaptive":[137],"spectral":[138],"routing},":[139],"which":[140],"partitions":[141],"via":[145,202],"empirical":[147],"Fiedler":[148],"eigenvector":[149],"dependency":[152],"graph":[153],"achieves":[155],"$\\mathcal{O}(\\sqrt{\\Tmix/n})$":[159],"up":[160],"to":[161],"lower-order":[163],"geometric":[164],"cut":[165],"term":[166],"subclass,":[170],"without":[171],"knowledge":[172],"$\\Tmix$.":[174],"Experiments":[175],"synthetic":[177],"chains,":[179],"2D":[180],"128-dataset":[184],"UCR":[185],"archive,":[186],"Atari":[188],"DQN":[189],"validate":[191],"theoretical":[193],"predictions.":[194],"Consequences":[195],"deep":[197],"RL":[198],"target":[199],"variance,":[200],"scalability":[201],"Nystr\u00f6m":[203],"approximation,":[204],"non-stationarity":[207],"are":[208],"developed":[209],"supporting":[211],"material":[212],"appendix.":[215]},"counts_by_year":[],"updated_date":"2026-04-17T06:04:52.305304","created_date":"2026-04-17T00:00:00"}