{"id":"https://openalex.org/W7220914498","doi":"https://doi.org/10.48550/arxiv.2610.07292","title":"Assumption-lean logistic regression with missing covariates","display_name":"Assumption-lean logistic regression with missing covariates","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220914498","doi":"https://doi.org/10.48550/arxiv.2610.07292"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.07292","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07292","pdf_url":"https://arxiv.org/pdf/2610.07292","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/2610.07292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044280357","display_name":"Jyotishka Ray Choudhury","orcid":"https://orcid.org/0000-0002-7070-683X","observed_orcids":["https://orcid.org/0000-0002-7070-683X"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Choudhury, Jyotishka Ray","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006739964","display_name":"Kabir Aladin Chandrasekher","orcid":"https://orcid.org/0000-0002-5442-1455","observed_orcids":["https://orcid.org/0000-0002-5442-1455"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Verchand, Kabir Aladin","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003721823","display_name":"Richard J. Samworth","orcid":"https://orcid.org/0000-0003-2426-4679","observed_orcids":["https://orcid.org/0000-0003-2426-4679"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samworth, Richard J.","raw_affiliation_strings":["Department of Data Sciences and Operations , University of Southern California Statistical Laboratory ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Sciences and Operations , University of Southern California Statistical Laboratory ,","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085869933","display_name":"Ashwin Pananjady","orcid":"https://orcid.org/0000-0003-0824-9815","observed_orcids":["https://orcid.org/0000-0003-0824-9815"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Pananjady, Ashwin","raw_affiliation_strings":["School of Industrial and Systems Engineering , Georgia Institute of Technology \u2022","University of Cambridge School of Electrical and Computer Engineering ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering , Georgia Institute of Technology \u2022","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"University of Cambridge School of Electrical and Computer Engineering ,","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9199000000953674,"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"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9199000000953674,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.016300000250339508,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.013899999670684338,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/missing-covariates","display_name":"missing covariates","score":0.8930000066757202},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.9700000286102295},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.5669999718666077},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"stochastic approximation","score":0.9639999866485596},{"id":"https://openalex.org/keywords/missing-completely-at-random","display_name":"missing completely at random","score":0.906000018119812},{"id":"https://openalex.org/keywords/signal-reconstruction","display_name":"signal reconstruction","score":0.527999997138977},{"id":"https://openalex.org/keywords/minimax-lower-bounds","display_name":"minimax lower bounds","score":0.7950000166893005},{"id":"https://openalex.org/keywords/information-theoretic-lower-bounds","display_name":"information-theoretic lower bounds","score":0.7139999866485596},{"id":"https://openalex.org/keywords/parameter-estimation","display_name":"parameter estimation","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.8815000057220459},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.8208000063896179},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.65829998254776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6510999798774719},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.5697000026702881},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5669999718666077},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.5127000212669373},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C41587187","wikidata":"https://www.wikidata.org/wiki/Q1501882","display_name":"Generalized linear model","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C204016326","wikidata":"https://www.wikidata.org/wiki/Q5401384","display_name":"Estimating equations","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C65778772","wikidata":"https://www.wikidata.org/wiki/Q12345341","display_name":"Asymptotic distribution","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C94465730","wikidata":"https://www.wikidata.org/wiki/Q589603","display_name":"Logistic distribution","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.07292","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07292","pdf_url":"https://arxiv.org/pdf/2610.07292","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.2610.07292","doi":"https://doi.org/10.48550/arxiv.2610.07292","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.07292","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.07292","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07292","pdf_url":"https://arxiv.org/pdf/2610.07292","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":[{"id":"https://openalex.org/G7933359309","display_name":"CIF: Medium: Learning, refining, and understanding models through relational feedback","funder_award_id":"2107455","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220914498.pdf","grobid_xml":"https://content.openalex.org/works/W7220914498.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2100028280","https://openalex.org/W3001934349","https://openalex.org/W4407012644","https://openalex.org/W4415336017","https://openalex.org/W4416212490","https://openalex.org/W7082147730","https://openalex.org/W7129596897","https://openalex.org/W7140991797"],"related_works":["https://openalex.org/W2003333473","https://openalex.org/W7140187409","https://openalex.org/W2068168411","https://openalex.org/W2998409966","https://openalex.org/W4409800385","https://openalex.org/W1998578978","https://openalex.org/W1994545448","https://openalex.org/W60021262","https://openalex.org/W2000378434","https://openalex.org/W3195785749"],"abstract_inverted_index":{"Missing":[0],"covariates":[1,157],"are":[2,39,158],"frequently":[3],"encountered":[4],"in":[5,43,57,62,70,100,109,173,204,259],"supervised":[6],"learning":[7],"problems,":[8],"and":[9,36,50,137,145,224],"classical":[10],"methods":[11,35,74],"for":[12,22,41,90],"estimation":[13,99],"using":[14,235],"such":[15,66,73],"data":[16],"use":[17],"carefully":[18],"chosen":[19],"imputation":[20],"schemes":[21],"missing":[23,104,159,201],"data,":[24],"or":[25],"likelihood":[26],"approximations":[27],"that":[28,127,139,156,186,196,229,249,251],"lead":[29],"to":[30],"nonconvex":[31],"$M$-estimation":[32],"problems.":[33],"These":[34],"their":[37],"relatives":[38],"suitable":[40],"scenarios":[42],"which":[44,211],"the":[45,81,88,95,110,114,154,167,171,176,191,205],"covariate":[46,82,115,213],"distribution":[47,83,116],"is":[48,84,117,128,142,214,257],"known,":[49],"more":[51],"broadly,":[52],"have":[53],"enjoyed":[54],"tremendous":[55],"success":[56],"linear":[58],"models.":[59],"But":[60],"even":[61],"basic":[63],"nonlinear":[64],"problems":[65],"as":[67],"logistic":[68,101],"regression":[69,102],"moderate":[71],"dimensions,":[72],"can":[75,230],"experience":[76],"drastic":[77],"failure":[78],"modes":[79],"when":[80],"unknown.":[85],"Motivated":[86],"by":[87],"need":[89],"reliable":[91],"alternatives,":[92],"we":[93,107],"consider":[94],"problem":[96],"of":[97,170,175],"parameter":[98],"with":[103,132,199,207,217,244],"covariates.":[105],"Crucially,":[106],"operate":[108],"assumption-lean":[111],"setting":[112,206],"where":[113],"unknown":[118],"(but":[119],"bounded).":[120],"We":[121,239],"design":[122],"a":[123,133,260],"stochastic":[124],"approximation":[125],"method":[126,188],"based":[129],"on":[130,227,255],"$Z$-estimation":[131],"novel":[134],"monotone":[135],"operator,":[136],"establish":[138],"our":[140,187,220,241],"algorithm":[141],"computationally":[143],"efficient":[144],"achieves":[146],"provable":[147],"signal":[148],"recovery":[149],"at":[150,161],"parametric":[151],"rates":[152],"under":[153],"hypothesis":[155],"completely":[160],"random.":[162],"Our":[163],"theory":[164],"sharply":[165],"characterizes":[166],"$\\ell_2^2$":[168],"risk":[169],"estimator":[172,195],"terms":[174],"missingness":[177,209],"profile,":[178],"accommodating":[179],"heterogeneous":[180],"observation":[181],"probabilities.":[182],"Importantly,":[183],"it":[184],"shows":[185],"always":[189],"outperforms":[190],"de":[192],"facto":[193],"``complete-case''":[194],"ignores":[197],"observations":[198],"any":[200],"data.":[202],"Even":[203],"homogeneous":[208],"(in":[210],"each":[212],"observed":[215],"independently":[216],"probability":[218],"$q$),":[219],"bounds":[221,243,248],"exhibit":[222],"intricate":[223,253],"nonstandard":[225],"dependence":[226,254],"$q$":[228,256],"yield":[231],"significant":[232],"improvements":[233],"over":[234],"only":[236],"complete":[237],"cases.":[238],"complement":[240],"upper":[242],"new":[245],"information-theoretic":[246],"lower":[247],"show":[250],"this":[252],"fundamental":[258],"minimax":[261],"sense.":[262]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}