{"id":"https://openalex.org/W7160512677","doi":"https://doi.org/10.48550/arxiv.2605.05189","title":"Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval","display_name":"Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160512677","doi":"https://doi.org/10.48550/arxiv.2605.05189"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05189","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05189","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.05189","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092998289","display_name":"Nicholas Barnfield","orcid":"https://orcid.org/0009-0003-9895-8347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barnfield, Nicholas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130981999","display_name":"Juno Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Juno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004602170","display_name":"Eshaan Nichani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nichani, Eshaan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135601751","display_name":"Jason D. Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jason D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038111389","display_name":"Yue M. Lu","orcid":"https://orcid.org/0000-0002-5174-2595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yue M.","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6908000111579895,"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":0.6908000111579895,"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/T11716","display_name":"Random Matrices and Applications","score":0.045499999076128006,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.03669999912381172,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6396999955177307},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.487199991941452},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.4733999967575073},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.4237000048160553},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4146000146865845},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4108000099658966},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4059000015258789},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4025999903678894}],"concepts":[{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5353999733924866},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4424000084400177},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C170122806","wikidata":"https://www.wikidata.org/wiki/Q1914828","display_name":"Linear scale","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37720000743865967},{"id":"https://openalex.org/C64812099","wikidata":"https://www.wikidata.org/wiki/Q176604","display_name":"Random matrix","level":3,"score":0.37720000743865967},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3709999918937683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35260000824928284},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C44292817","wikidata":"https://www.wikidata.org/wiki/Q333871","display_name":"Orthogonal matrix","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C122048520","wikidata":"https://www.wikidata.org/wiki/Q2913954","display_name":"Percentile","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C70970002","wikidata":"https://www.wikidata.org/wiki/Q189434","display_name":"Multiplexer","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C53442348","wikidata":"https://www.wikidata.org/wiki/Q745101","display_name":"Content-addressable memory","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05189","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05189","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.05189","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05189","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7671516537666321}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"How":[0],"many":[1],"key-value":[2],"associations":[3,75],"can":[4],"a":[5,85,144,156,188,196,205,230],"$d\\times":[6],"d$":[7],"linear":[8,98],"memory":[9,27,71],"store?":[10],"We":[11,65,111],"show":[12,45],"that":[13,46,67,90,148],"the":[14,20,26,32,41,58,68,91,101,104,117,123,131,140,152,165,168,183,200,217,236],"answer":[15],"depends":[16],"not":[17,121],"only":[18],"on":[19,31],"$d^2$":[21],"degrees":[22],"of":[23,108,151,220],"freedom":[24],"in":[25,155,199],"matrix,":[28],"but":[29,127],"also":[30],"retrieval":[33,163],"criterion.":[34],"In":[35],"an":[36,178],"isotropic":[37],"Gaussian":[38],"model":[39],"for":[40,96,182],"stored":[42],"pairs,":[43],"we":[44,138,176],"top-1":[47,239],"retrieval,":[48,115],"where":[49,116],"every":[50],"signal":[51],"must":[52],"beat":[53],"its":[54],"largest":[55],"distractor,":[56],"requires":[57],"logarithmic":[59],"model-size":[60],"scale":[61,83,170],"$d^2\\asymp":[62,171],"n\\log":[63],"n$.":[64,172,243],"prove":[66],"correlation":[69],"matrix":[70],"construction,":[72],"which":[73],"stores":[74],"by":[76],"superposing":[77],"key-target":[78],"outer":[79],"products,":[80],"achieves":[81],"this":[82,136,161],"through":[84,187],"sharp":[86,238],"phase":[87],"transition,":[88],"and":[89,211,214,226],"same":[92],"scaling":[93],"is":[94,103],"necessary":[95],"any":[97],"memory.":[99],"Thus":[100],"logarithm":[102],"intrinsic":[105],"extreme-value":[106],"price":[107],"winner-take-all":[109],"decoding.":[110],"next":[112],"consider":[113],"listwise":[114,162],"correct":[118,153],"target":[119,154],"need":[120],"be":[122],"unique":[124],"top-scoring":[125],"item":[126],"should":[128],"remain":[129],"among":[130],"strongest":[132],"candidates.":[133],"To":[134],"formalize":[135],"regime,":[137],"propose":[139],"Tail-Average":[141],"Margin":[142],"(TAM),":[143],"convex":[145],"upper-tail":[146],"criterion":[147],"certifies":[149],"inclusion":[150],"controlled":[157],"candidate":[158],"list.":[159],"Under":[160],"criterion,":[164],"capacity":[166],"follows":[167],"quadratic":[169],"At":[173],"load":[174,208],"$n/d^2\\to\u03b1$,":[175],"develop":[177],"exact":[179],"asymptotic":[180],"theory":[181,194],"TAM":[184],"empirical-risk":[185],"minimizer":[186],"two-parameter":[189],"scalar":[190],"variational":[191],"principle.":[192],"The":[193],"has":[195],"rich":[197],"phenomenology:":[198],"ridgeless":[201],"limit":[202],"it":[203,215],"yields":[204],"closed-form":[206],"critical":[207],"separating":[209],"satisfiable":[210],"unsatisfiable":[212],"phases,":[213],"predicts":[216],"limiting":[218],"laws":[219],"true":[221],"scores,":[222,224],"competitor":[223],"margins,":[225],"percentile":[227],"profiles.":[228],"Finally,":[229],"small-tail":[231],"extrapolation":[232],"further":[233],"leads":[234],"to":[235],"conjectural":[237],"threshold":[240],"$d^2\\sim":[241],"2n\\log":[242]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-08T00:00:00"}