{"id":"https://openalex.org/W7172390852","doi":"https://doi.org/10.48550/arxiv.2608.01032","title":"The Fourth Quadrant: A Stylized View of Benign Misfitting","display_name":"The Fourth Quadrant: A Stylized View of Benign Misfitting","publication_year":2026,"publication_date":"2026-08-02","ids":{"openalex":"https://openalex.org/W7172390852","doi":"https://doi.org/10.48550/arxiv.2608.01032"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.01032","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.01032","pdf_url":"https://arxiv.org/pdf/2608.01032","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/2608.01032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055069190","display_name":"Gireeja V. Ranade","orcid":"https://orcid.org/0000-0002-6747-4492","observed_orcids":["https://orcid.org/0000-0002-6747-4492"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranade, Gireeja","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079317491","display_name":"Anant Sahai","orcid":"https://orcid.org/0000-0001-9263-7719","observed_orcids":["https://orcid.org/0000-0001-9263-7719"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sahai, Anant","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6714000105857849,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6714000105857849,"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":0.06710000336170197,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.06120000034570694,"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/interpolation","display_name":"interpolation","score":0.38499999046325684},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.46399998664855957},{"id":"https://openalex.org/keywords/training-error","display_name":"training error","score":0.48399999737739563},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.6859999895095825},{"id":"https://openalex.org/keywords/high-dimensional-regression","display_name":"high-dimensional regression","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.7368000149726868},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5406000018119812},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.46459999680519104},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.37529999017715454},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33809998631477356},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C194531419","wikidata":"https://www.wikidata.org/wiki/Q17104825","display_name":"Nuisance parameter","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.01032","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.01032","pdf_url":"https://arxiv.org/pdf/2608.01032","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.2608.01032","doi":"https://doi.org/10.48550/arxiv.2608.01032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.01032","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:2608.01032","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.01032","pdf_url":"https://arxiv.org/pdf/2608.01032","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/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7170043270","display_name":"SII-Center: SpectrumX \u2013 An NSF Spectrum Innovation Center","funder_award_id":"2132700","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7498860972","display_name":"CAREER: A deeper look at state-dependent noise in systems","funder_award_id":"2240031","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"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7172390852.pdf","grobid_xml":"https://content.openalex.org/works/W7172390852.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W198508004","https://openalex.org/W1991769471","https://openalex.org/W1992208280","https://openalex.org/W1994616650","https://openalex.org/W2012816719","https://openalex.org/W2015904350","https://openalex.org/W2066459155","https://openalex.org/W2109962983","https://openalex.org/W2116485279","https://openalex.org/W2133214726","https://openalex.org/W2134130436","https://openalex.org/W2141902405","https://openalex.org/W2152471841","https://openalex.org/W2154752110","https://openalex.org/W2157989362","https://openalex.org/W2169128714","https://openalex.org/W2432567885","https://openalex.org/W2436219157","https://openalex.org/W2497770847","https://openalex.org/W2567588361","https://openalex.org/W2622263826","https://openalex.org/W2749581528","https://openalex.org/W2763894180","https://openalex.org/W2768267830","https://openalex.org/W2900167092","https://openalex.org/W2903697572","https://openalex.org/W2910589063","https://openalex.org/W2912811302","https://openalex.org/W2922153390","https://openalex.org/W2923764619","https://openalex.org/W2924580837","https://openalex.org/W2950181023","https://openalex.org/W2954975122","https://openalex.org/W2963518130","https://openalex.org/W3009686669","https://openalex.org/W3015353261","https://openalex.org/W3113004165","https://openalex.org/W3196464222","https://openalex.org/W3202424289","https://openalex.org/W3203303987","https://openalex.org/W3206471146","https://openalex.org/W4205228770","https://openalex.org/W4224277381","https://openalex.org/W4252713891","https://openalex.org/W4288057780","https://openalex.org/W4321230989","https://openalex.org/W4385947742","https://openalex.org/W4391131725","https://openalex.org/W4391158924","https://openalex.org/W4391211950","https://openalex.org/W4391546480","https://openalex.org/W4391546531","https://openalex.org/W4391871165","https://openalex.org/W4392781932","https://openalex.org/W4405956499","https://openalex.org/W4415797373","https://openalex.org/W4415797471","https://openalex.org/W4416246526","https://openalex.org/W4417256404","https://openalex.org/W6948430870","https://openalex.org/W7103755733","https://openalex.org/W7117163384","https://openalex.org/W7133207696","https://openalex.org/W7162411664"],"related_works":["https://openalex.org/W4221154618","https://openalex.org/W4414816532","https://openalex.org/W4226372400","https://openalex.org/W4221142205","https://openalex.org/W2038774192","https://openalex.org/W4388538746","https://openalex.org/W4221163258","https://openalex.org/W117623024","https://openalex.org/W2064765946","https://openalex.org/W2954975122"],"abstract_inverted_index":{"Training":[0,44],"error":[1,12,139,145,200],"is":[2,13,78,103],"what":[3],"we":[4,16],"can":[5],"observe":[6],"on":[7,89],"a":[8,25,104,192,211],"training":[9,31,72,119,144,182,218,227],"set;":[10],"test":[11,49,138,199],"the":[14,63,71,75,93,100,118,123,132,170,185,205,221,226],"quantity":[15],"care":[17],"about.":[18],"We":[19,61,126],"study":[20],"squared-error":[21],"linear":[22,68,82],"regression":[23],"in":[24,70,92],"deterministic":[26],"$(d+1)$-dimensional":[27],"single-spike":[28],"model.":[29],"Each":[30],"vector":[32],"has":[33],"spike":[34,76],"coordinate":[35],"$\\sqrt\u03b3$,":[36],"$\u03b3>1$,":[37],"and":[38,57],"equal-norm,":[39],"mutually":[40],"orthogonal":[41],"nuisance":[42,222],"components.":[43],"labels":[45],"are":[46,51],"$1$.":[47],"Fresh":[48],"points":[50],"centered":[52],"Gaussian":[53],"with":[54,99,147,191],"covariance":[55],"$\\operatorname{diag}(\u03b3,1,\\ldots,1)$":[56],"noise-free":[58],"label":[59],"$x[1]/\\sqrt\u03b3$.":[60],"compute":[62],"exact":[64],"train--test":[65],"tradeoff":[66],"for":[67,225],"predictors":[69,83],"span.":[73],"When":[74],"direction":[77],"unknown,":[79],"allowing":[80],"all":[81],"does":[84],"not":[85],"improve":[86],"this":[87,128,202],"tradeoff,":[88],"average":[90],"or":[91,131],"worst":[94],"case":[95],"over":[96],"directions":[97],"consistent":[98],"data.":[101],"There":[102],"range":[105],"of":[106],"training-set":[107],"sizes":[108],"where":[109],"every":[110],"span":[111,156,177,207],"predictor":[112,157,208],"that":[113],"generalizes":[114],"well":[115],"must":[116],"fit":[117],"data":[120],"worse":[121],"than":[122],"zero":[124,142],"predictor.":[125],"call":[127],"benign":[129],"misfitting,":[130],"fourth":[133],"quadrant.":[134],"At":[135],"its":[136],"sharpest,":[137],"tends":[140],"to":[141,152,159,210],"while":[143,164,214],"diverges,":[146],"both":[148],"zero-predictor":[149],"errors":[150],"normalized":[151],"one.":[153],"The":[154],"best":[155,206],"begins":[158],"generalize":[160],"when":[161],"$n\\gg":[162,167],"d/\u03b3^2$,":[163],"interpolation":[165],"needs":[166],"d/\u03b3$.":[168],"In":[169],"intervening":[171],"window":[172],"$d/\u03b3^2\\ll":[173],"n\\ll":[174],"d/\u03b3$,":[175],"useful":[176],"prediction":[178],"lies":[179],"beyond":[180],"interpolation:":[181],"predictions":[183],"overshoot":[184],"labels.":[186],"One-pass":[187],"stochastic":[188],"gradient":[189],"descent":[190],"large":[193,216],"constant":[194],"learning":[195],"rate":[196],"attains":[197],"small":[198],"throughout":[201],"window,":[203],"matching":[204],"up":[209],"logarithmic":[212],"factor,":[213],"leaving":[215],"empirical":[217],"error.":[219],"Finally,":[220],"component":[223],"responsible":[224],"misfit":[228],"also":[229],"controls":[230],"adversarial":[231],"sensitivity.":[232]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-05T00:00:00"}