{"id":"https://openalex.org/W7151502126","doi":"https://doi.org/10.48550/arxiv.2604.04228","title":"Robust Regression with Adaptive Contamination in Response: Optimal Rates and Computational Barriers","display_name":"Robust Regression with Adaptive Contamination in Response: Optimal Rates and Computational Barriers","publication_year":2026,"publication_date":"2026-04-05","ids":{"openalex":"https://openalex.org/W7151502126","doi":"https://doi.org/10.48550/arxiv.2604.04228"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.04228","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04228","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.2604.04228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133133557","display_name":"Ilias Diakonikolas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diakonikolas, Ilias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133126440","display_name":"Chao Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133091808","display_name":"Daniel M. Kane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kane, Daniel M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046067745","display_name":"Ankit Pensia","orcid":"https://orcid.org/0000-0003-3509-1224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pensia, Ankit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133065150","display_name":"Dong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Dong","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/T10136","display_name":"Statistical Methods and Inference","score":0.35510000586509705,"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":0.35510000586509705,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.2773999869823456,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.0869000032544136,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/estimator","display_name":"Estimator","score":0.6136000156402588},{"id":"https://openalex.org/keywords/covariate","display_name":"Covariate","score":0.598800003528595},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.5404999852180481},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5175999999046326},{"id":"https://openalex.org/keywords/robust-regression","display_name":"Robust regression","score":0.5084999799728394},{"id":"https://openalex.org/keywords/contamination","display_name":"Contamination","score":0.49079999327659607},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4650999903678894},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4611999988555908}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6315000057220459},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6136000156402588},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.598800003528595},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C70259352","wikidata":"https://www.wikidata.org/wiki/Q1847839","display_name":"Robust regression","level":3,"score":0.5084999799728394},{"id":"https://openalex.org/C112570922","wikidata":"https://www.wikidata.org/wiki/Q60528603","display_name":"Contamination","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.43290001153945923},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.4171999990940094},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40139999985694885},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.39399999380111694},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.3725000023841858},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.04228","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04228","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.2604.04228","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04228","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":{"We":[0],"study":[1],"robust":[2,203],"regression":[3,204],"under":[4,90],"a":[5,47,83,109,194],"contamination":[6,27,44,107,126],"model":[7,150],"in":[8,19,69,141,160,202],"which":[9],"covariates":[10,31,72],"are":[11],"clean":[12,71,206],"while":[13],"the":[14,24,43,54,66,70,96,106,123,135,145,148,161,173,184],"responses":[15,33],"may":[16,34],"be":[17,35,74,188],"corrupted":[18],"an":[20,79,152],"adaptive":[21],"manner.":[22],"Unlike":[23],"classical":[25],"Huber's":[26,142],"model,":[28,98],"where":[29],"both":[30],"and":[32,37,166,199],"contaminated":[36],"consistent":[38],"estimation":[39,85],"is":[40,46,108,116],"impossible":[41],"when":[42,105],"proportion":[45],"non-vanishing":[48],"constant,":[49],"it":[50],"turns":[51],"out":[52],"that":[53,65,81,88,128,172,183],"clean-covariate":[55],"setting":[56],"admits":[57],"strictly":[58],"improved":[59,100],"statistical":[60],"guarantees.":[61],"Specifically,":[62],"we":[63,155],"show":[64],"additional":[67],"information":[68],"can":[73],"carefully":[75],"exploited":[76],"to":[77,95],"construct":[78],"estimator":[80],"achieves":[82],"better":[84],"rate":[86,101],"than":[87],"attainable":[89],"Huber":[91,97,149],"contamination.":[92],"In":[93],"contrast":[94],"this":[99],"implies":[102],"consistency":[103],"even":[104],"constant.":[110],"A":[111],"matching":[112],"minimax":[113],"lower":[114,138,169],"bound":[115,139],"established":[117],"using":[118],"Fano's":[119],"inequality":[120],"together":[121],"with":[122,205],"construction":[124],"of":[125,163],"processes":[127],"match":[129],"$m>":[130],"2$":[131],"distributions":[132],"simultaneously,":[133],"extending":[134],"previous":[136],"two-point":[137],"argument":[140],"setting.":[143],"Despite":[144],"improvement":[146],"over":[147],"from":[151],"information-theoretic":[153,185,198],"perspective,":[154],"provide":[156],"formal":[157],"evidence":[158],"--":[159,171],"form":[162],"Statistical":[164],"Query":[165],"Low-Degree":[167],"Polynomial":[168],"bounds":[170],"problem":[174],"exhibits":[175],"strong":[176],"information-computation":[177],"gaps.":[178],"Our":[179],"results":[180],"strongly":[181],"suggest":[182],"improvements":[186],"cannot":[187],"achieved":[189],"by":[190],"polynomial-time":[191],"algorithms,":[192],"revealing":[193],"fundamental":[195],"gap":[196],"between":[197],"computational":[200],"limits":[201],"covariates.":[207]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}