{"id":"https://openalex.org/W7105302274","doi":"https://doi.org/10.48550/arxiv.2511.05736","title":"Near-Exponential Savings for Mean Estimation with Active Learning","display_name":"Near-Exponential Savings for Mean Estimation with Active Learning","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W7105302274","doi":"https://doi.org/10.48550/arxiv.2511.05736"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.05736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05736","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2511.05736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Morimoto, Julian M.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morimoto, Julian M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Goldin, Jacob","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goldin, Jacob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ho, Daniel E.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho, Daniel E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9724000096321106,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9724000096321106,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.014299999922513962,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0010000000474974513,"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":0.6868000030517578},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.6628999710083008},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.6628999710083008},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.476500004529953},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.41620001196861267}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6868000030517578},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6136000156402588},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32679998874664307},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.28360000252723694},{"id":"https://openalex.org/C137345334","wikidata":"https://www.wikidata.org/wiki/Q7303350","display_name":"Recursive partitioning","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.05736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05736","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2511.05736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05736","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"We":[0,41,166],"study":[1],"the":[2,7,25,81,84,94,102,107,114,131,135,147,183],"problem":[3],"of":[4,9,19,83,101,111],"efficiently":[5],"estimating":[6],"mean":[8],"a":[10,16,76,90,99,119],"$k$-class":[11],"random":[12],"variable,":[13],"$Y$,":[14],"using":[15,172,182],"limited":[17],"number":[18],"labels,":[20],"$N$,":[21],"in":[22,142,186],"settings":[23],"where":[24,71],"analyst":[26],"has":[27],"access":[28],"to":[29,48,123,152,161],"auxiliary":[30],"information":[31],"(i.e.:":[32],"covariates)":[33],"$X$":[34],"that":[35,58,105],"may":[36],"be":[37,180],"informative":[38],"about":[39],"$Y$.":[40,112],"propose":[42],"an":[43,54],"active":[44,153],"learning":[45,154],"algorithm":[46,52],"(\"PartiBandits\")":[47],"estimate":[49],"$\\mathbb{E}[Y]$.":[50],"The":[51],"yields":[53],"estimate,":[55],"$\\widehat\u03bc_{\\text{PB}}$,":[56],"such":[57],"$\\left(":[59],"\\widehat\u03bc_{\\text{PB}}":[60],"-":[61],"\\mathbb{E}[Y]\\right)^2$":[62],"is":[63,75,80,88],"$\\tilde{\\mathcal{O}}\\left(":[64],"\\frac{\u03bd+":[65],"\\exp(c":[66],"\\cdot":[67],"(-N/\\log(N)))":[68],"}{N}":[69],"\\right)$,":[70],"$c":[72],">":[73],"0$":[74],"constant":[77],"and":[78,134,149],"$\u03bd$":[79],"risk":[82],"Bayes-optimal":[85],"classifier.":[86],"PartiBandits":[87,145,184],"essentially":[89],"two-stage":[91],"algorithm.":[92],"In":[93,113],"first":[95],"stage,":[96],"it":[97,117],"learns":[98],"partition":[100],"unlabeled":[103],"data":[104],"shrinks":[106],"average":[108],"conditional":[109],"variance":[110],"second":[115],"stage":[116],"uses":[118],"UCB-style":[120],"subroutine":[121],"(\"WarmStart-UCB\")":[122],"request":[124],"labels":[125],"from":[126],"each":[127],"stratum":[128],"round-by-round.":[129],"Both":[130],"main":[132],"algorithm's":[133],"subroutine's":[136],"convergence":[137],"rates":[138],"are":[139],"minimax":[140],"optimal":[141],"classical":[143],"settings.":[144],"bridges":[146],"UCB":[148],"disagreement-based":[150],"approaches":[151,158],"despite":[155],"these":[156],"two":[157],"being":[159],"designed":[160],"tackle":[162],"very":[163],"different":[164],"tasks.":[165],"illustrate":[167],"our":[168],"methods":[169,178],"through":[170],"simulation":[171],"nationwide":[173],"electronic":[174],"health":[175],"records.":[176],"Our":[177],"can":[179],"implemented":[181],"package":[185],"R.":[187]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-12T00:00:00"}