{"id":"https://openalex.org/W7161018235","doi":"https://doi.org/10.48550/arxiv.2605.11911","title":"Understanding Sample Efficiency in Predictive Coding","display_name":"Understanding Sample Efficiency in Predictive Coding","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161018235","doi":"https://doi.org/10.48550/arxiv.2605.11911"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11911","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.2605.11911","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092761803","display_name":"Gaspard Oliviers","orcid":"https://orcid.org/0009-0004-6752-8296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliviers, Gaspard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030843412","display_name":"Elene Lominadze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lominadze, Elene","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136071698","display_name":"Rafal Bogacz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogacz, Rafal","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1534000039100647,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1534000039100647,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15289999544620514,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11299999803304672,"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/backpropagation","display_name":"Backpropagation","score":0.6118000149726868},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6014000177383423},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.5996999740600586},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4902999997138977},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.462799996137619},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46160000562667847},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.3499000072479248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625999808311462},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6118000149726868},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.5996999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5934000015258789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5756000280380249},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11911","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.2605.11911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11911","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Predictive":[0],"Coding":[1],"(PC)":[2],"is":[3,38,88,116,122],"an":[4],"influential":[5],"account":[6],"of":[7,11,52,64,85,154,164,182],"cortical":[8],"learning.":[9],"Much":[10],"recent":[12],"work":[13,177],"has":[14],"focused":[15],"on":[16],"comparing":[17],"PC":[18,25,34,69,115,142,165,189,199],"to":[19,22,90,203],"Backpropagation":[20],"(BP)":[21],"find":[23,160],"whether":[24],"offers":[26],"any":[27],"advantages.":[28],"Small":[29],"scale":[30],"experiments":[31],"show":[32,111],"that":[33,37,112],"enables":[35],"learning":[36,65,113,185],"more":[39,117],"sample":[40],"efficient":[41,118],"and":[42,68,98,128,143,156,159,195],"effective":[43],"in":[44,66,82,106,114,125,141,167,192],"many":[45],"contexts,":[46],"though":[47],"a":[48,71,179],"thorough":[49],"theoretical":[50],"understanding":[51,181],"the":[53,62,80,83,86,91,161,183],"phenomena":[54],"remains":[55],"elusive.":[56],"To":[57],"address":[58],"this,":[59],"we":[60],"quantify":[61],"efficiency":[63,186],"BP":[67,191],"through":[70,147],"metric":[72],"called":[73],"``target":[74],"alignment'',":[75],"which":[76,121],"measures":[77],"how":[78,198],"closely":[79],"change":[81],"output":[84,92],"network":[87],"aligned":[89],"prediction":[93],"error.":[94],"We":[95,110,131,149],"then":[96],"derive":[97,133],"empirically":[99],"validate":[100,144],"analytical":[101],"expressions":[102],"for":[103,136,188],"target":[104,139],"alignment":[105,140],"Deep":[107],"Linear":[108],"Networks.":[109],"than":[119],"BP,":[120],"especially":[123],"pronounced":[124],"deep,":[126],"narrow":[127],"pre-trained":[129],"networks.":[130],"also":[132],"exact":[134],"conditions":[135],"guaranteed":[137],"optimal":[138],"our":[145],"findings":[146],"experiments.":[148],"study":[150],"full":[151],"training":[152],"trajectories":[153],"linear":[155],"non-linear":[157],"models,":[158],"predicted":[162],"benefits":[163],"persist":[166],"practice":[168],"even":[169],"when":[170],"some":[171],"assumptions":[172],"are":[173],"violated.":[174],"Overall,":[175],"this":[176],"provides":[178],"mechanistic":[180],"higher":[184],"observed":[187],"over":[190],"previous":[193],"works,":[194],"can":[196],"guide":[197],"should":[200],"be":[201],"parametrised":[202],"learn":[204],"most":[205],"effectively.":[206]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}