{"id":"https://openalex.org/W7203860069","doi":"https://doi.org/10.48550/arxiv.2608.18402","title":"Algorithms for adaptive and heteroskedastic linear regression at the computational threshold","display_name":"Algorithms for adaptive and heteroskedastic linear regression at the computational threshold","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7203860069","doi":"https://doi.org/10.48550/arxiv.2608.18402"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.18402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18402","pdf_url":"https://arxiv.org/pdf/2608.18402","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/2608.18402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049956691","display_name":"Spencer Compton","orcid":"https://orcid.org/0009-0009-4161-4651","observed_orcids":["https://orcid.org/0009-0009-4161-4651"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Compton, Spencer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081583404","display_name":"Tselil Schramm","orcid":"https://orcid.org/0000-0002-8494-5778","observed_orcids":["https://orcid.org/0000-0002-8494-5778"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schramm, Tselil","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":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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.31049999594688416,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.31049999594688416,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.14990000426769257,"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/T10136","display_name":"Statistical Methods and Inference","score":0.10740000009536743,"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/noisy-labels","display_name":"label noise","score":0.8840000033378601},{"id":"https://openalex.org/keywords/finite-sample-estimation","display_name":"finite-sample estimation","score":0.6840000152587891},{"id":"https://openalex.org/keywords/log-concave-distributions","display_name":"log-concave distributions","score":0.7580000162124634}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7950000166893005},{"id":"https://openalex.org/C101104100","wikidata":"https://www.wikidata.org/wiki/Q1063540","display_name":"Heteroscedasticity","level":2,"score":0.7315000295639038},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.6952000260353088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6890000104904175},{"id":"https://openalex.org/C32224588","wikidata":"https://www.wikidata.org/wiki/Q7250175","display_name":"Proper linear model","level":4,"score":0.5447999835014343},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C2780617739","wikidata":"https://www.wikidata.org/wiki/Q4680738","display_name":"Adaptive estimator","level":3,"score":0.4749000072479248},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4562000036239624},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.4530999958515167},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C70259352","wikidata":"https://www.wikidata.org/wiki/Q1847839","display_name":"Robust regression","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C164172150","wikidata":"https://www.wikidata.org/wiki/Q1782585","display_name":"Consistent estimator","level":4,"score":0.32589998841285706},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C97379794","wikidata":"https://www.wikidata.org/wiki/Q4503892","display_name":"Censored regression model","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C60316415","wikidata":"https://www.wikidata.org/wiki/Q6664520","display_name":"Local regression","level":4,"score":0.28790000081062317},{"id":"https://openalex.org/C162948026","wikidata":"https://www.wikidata.org/wiki/Q6553486","display_name":"Linear predictor function","level":5,"score":0.28790000081062317},{"id":"https://openalex.org/C149769383","wikidata":"https://www.wikidata.org/wiki/Q7520804","display_name":"Simple linear regression","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C35594927","wikidata":"https://www.wikidata.org/wiki/Q2265984","display_name":"Efficient estimator","level":4,"score":0.28029999136924744},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C179024874","wikidata":"https://www.wikidata.org/wiki/Q5395728","display_name":"Errors-in-variables models","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C134962040","wikidata":"https://www.wikidata.org/wiki/Q7606742","display_name":"Stein's unbiased risk estimate","level":5,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.18402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18402","pdf_url":"https://arxiv.org/pdf/2608.18402","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.2608.18402","doi":"https://doi.org/10.48550/arxiv.2608.18402","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.18402","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:2608.18402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18402","pdf_url":"https://arxiv.org/pdf/2608.18402","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/G4043511936","display_name":"CAREER: Optimal High-Dimensional Estimators Using Sum-of-Squares Proof Systems","funder_award_id":"2143246","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8748375404","display_name":"AF: Small: Memory Bounded Optimization and Learning","funder_award_id":"2341890","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/W7203860069.pdf","grobid_xml":"https://content.openalex.org/works/W7203860069.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W3027393933","https://openalex.org/W4225838216","https://openalex.org/W4392193692","https://openalex.org/W4417355683","https://openalex.org/W7130571303","https://openalex.org/W7133545230","https://openalex.org/W7151502126","https://openalex.org/W7160525753","https://openalex.org/W7204846020"],"related_works":["https://openalex.org/W4382322592","https://openalex.org/W2806473647","https://openalex.org/W6903911900","https://openalex.org/W3039117700","https://openalex.org/W7091188154","https://openalex.org/W2790269521","https://openalex.org/W4297676006","https://openalex.org/W7201954535","https://openalex.org/W4392120575","https://openalex.org/W2581201870"],"abstract_inverted_index":{"We":[0,35,76,149,228],"study":[1,199],"finite-sample":[2],"linear":[3,20,24,115,210],"regression":[4,21,25,105,189,211],"in":[5],"the":[6,16,29,47,52,58,64,117,142,173,200,208,222],"presence":[7],"of":[8,32,57,60,66,164,203],"varied":[9],"and":[10,18,46,106,127,179,221,246,257],"unknown":[11,50,124,217],"label":[12],"noise,":[13],"focusing":[14],"on":[15],"heteroskedastic":[17],"adaptive":[19,114,154],"models.":[22],"Heteroskedastic":[23],"models":[26],"settings":[27],"where":[28,43,213],"labels":[30,41],"are":[31,49,119,219],"varying":[33],"quality.":[34],"receive":[36],"$n$":[37],"pairs":[38],"$(X_i,Y_i)$":[39],"with":[40,81,172],"$Y_i=X_i^\\top\u03b2+\\varepsilon_i$,":[42],"$\\varepsilon_i\\sim":[44,226],"N(0,\u03c3_i^2)$":[45],"variances":[48],"to":[51,131,198,234],"estimator.":[53,196],"One":[54],"natural":[55],"measurement":[56],"difficulty":[59],"this":[61],"problem":[62],"is":[63,74,130,161,250],"number":[65],"samples":[67,218],"$m$":[68,73,216],"for":[69],"which":[70],"$\u03c3_i^2\\le1$":[71],"(larger":[72],"easier).":[75],"obtain":[77],"a":[78,133,151,162,194],"polynomial-time":[79,195,255],"estimator":[80,96,135,145,155,175,256],"rate":[82],"$\\tilde{O}((nd^3/m^4)^{1/6})$":[83],"when":[84,100],"$m\\gg":[85,101,111],"d^{3/4}n^{1/4}$,":[86,248],"as":[87,89,139,141,159,249],"well":[88,140],"nearly-matching":[90],"lower":[91,261],"bounds.":[92],"For":[93,183],"$d=O(1)$,":[94],"our":[95,128,253],"achieves":[97,169],"error":[98,170,225,235],"$o(1)$":[99],"n^{1/4}$,":[102],"whereas":[103],"$L_1$":[104],"other":[107],"traditional":[108],"approaches":[109],"require":[110],"n^{1/2}$.":[112],"In":[113],"regression,":[116],"errors":[118],"drawn":[120],"i.i.d.":[121],"from":[122],"an":[123,241],"distribution":[125],"$p$,":[126],"goal":[129],"design":[132],"generic":[134],"that":[136,146,176,187,230],"performs":[137],"nearly":[138],"best":[143],"custom":[144],"knows":[147,177],"$p$.":[148],"introduce":[150,207],"(computationally":[152],"inefficient)":[153],"that,":[156],"so":[157],"long":[158],"$p$":[160,178],"mixture":[163],"$k$":[165],"symmetric":[166],"log-concave":[167],"densities,":[168],"comparable":[171],"optimal":[174],"has":[180],"$\\tilde\u0398(n/k)$":[181],"samples.":[182],"$k=1$,":[184],"we":[185,206],"show":[186],"$L_q$":[188],"(with":[190],"data-dependent":[191],"$q$)":[192],"gives":[193],"Finally,":[197],"computational":[201],"limits":[202],"both":[204],"problems,":[205],"planted":[209],"problem,":[212],"$X_i\\sim":[214],"N(0,I_d)$,":[215],"noiseless,":[220],"rest":[223],"have":[224,240],"N(0,1)$.":[227],"conjecture":[229],"recovering":[231],"$\u03b2$":[232],"up":[233],"$\\ll\\sqrt{d/n}$":[236],"(or":[237],"exactly)":[238],"may":[239],"information-computation":[242],"gap":[243],"between":[244],"$m=d+1$":[245],"$m\\sim":[247],"suggested":[251],"by":[252],"near-matching":[254],"statistical":[258],"query":[259],"(SQ)":[260],"bound.":[262]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-22T00:00:00"}