{"id":"https://openalex.org/W7216087459","doi":"https://doi.org/10.48550/arxiv.2610.00753","title":"Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning","display_name":"Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7216087459","doi":"https://doi.org/10.48550/arxiv.2610.00753","pmid":"https://pubmed.ncbi.nlm.nih.gov/42856737","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13648819"},"language":"en","primary_location":{"id":"pmid:42856737","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856737","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Journal Article"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pubmed.ncbi.nlm.nih.gov/42856737/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117863655","display_name":"Syon Mansur","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mansur, Syon","raw_affiliation_strings":["Eye Institute University of California , Los Angeles Los Angeles , CA 90095 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eye Institute University of California , Los Angeles Los Angeles , CA 90095 , USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028769863","display_name":"Joel Zylberberg","orcid":"https://orcid.org/0000-0002-8208-5698","observed_orcids":["https://orcid.org/0000-0002-8208-5698"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zylberberg, Joel","raw_affiliation_strings":["Eye Institute University of California , Los Angeles Los Angeles , CA 90095 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eye Institute University of California , Los Angeles Los Angeles , CA 90095 , USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5562000274658203,"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":0.5562000274658203,"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/T10320","display_name":"Neural Networks and Applications","score":0.15489999949932098,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.11270000040531158,"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/self-supervised-learning","display_name":"self-supervised learning","score":0.9860000014305115},{"id":"https://openalex.org/keywords/network-width","display_name":"network width","score":0.9319999814033508},{"id":"https://openalex.org/keywords/network-depth","display_name":"network depth","score":0.9240000247955322},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7720000147819519},{"id":"https://openalex.org/keywords/representational-geometry","display_name":"representational geometry","score":0.953000009059906},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.8420000076293945},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5350000262260437},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.9108999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735000014305115},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6697999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6255999803543091},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6245999932289124},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.6000999808311462},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5813000202178955},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4702000021934509},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":4,"locations":[{"id":"pmid:42856737","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856737","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13648819","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856737/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Text"},{"id":"pmh:oai:arXiv.org:2610.00753","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00753","pdf_url":"https://arxiv.org/pdf/2610.00753","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.2610.00753","doi":"https://doi.org/10.48550/arxiv.2610.00753","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.00753","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":"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"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:13648819","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856737/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000858894","display_name":"Dynamic retinal coding in natural environments","funder_award_id":"R01EY036594","funder_id":"https://openalex.org/F4320337350","funder_display_name":"National Eye Institute"}],"funders":[{"id":"https://openalex.org/F4320306811","display_name":"Research to Prevent Blindness","ror":"https://ror.org/04drjs621"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337350","display_name":"National Eye Institute","ror":"https://ror.org/03wkg3b53"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216087459.pdf","grobid_xml":"https://content.openalex.org/works/W7216087459.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1993533483","https://openalex.org/W2588048611","https://openalex.org/W2768666611","https://openalex.org/W2919115771","https://openalex.org/W2982557070","https://openalex.org/W3016391357","https://openalex.org/W4210254869","https://openalex.org/W4306643150","https://openalex.org/W4387996733","https://openalex.org/W4393213810","https://openalex.org/W4415797979","https://openalex.org/W7127662003"],"related_works":["https://openalex.org/W2540556213","https://openalex.org/W7126223464","https://openalex.org/W4210544976","https://openalex.org/W4319323548","https://openalex.org/W2907407288","https://openalex.org/W3112479704","https://openalex.org/W4406884761","https://openalex.org/W2983785920","https://openalex.org/W3167699341","https://openalex.org/W7133224629"],"abstract_inverted_index":{"End-to-end":[0],"backpropagation":[1,61,128],"has":[2],"been":[3],"the":[4,14,50,83,106,124,156],"dominant":[5],"mode":[6],"of":[7,16,21,62,85,108,126,155],"training":[8,37,73,114,132],"in":[9,32,82,94,115,121,134,146,194],"deep":[10],"learning,":[11,87],"allowing":[12],"for":[13,91,187,201],"coordination":[15],"parameter":[17],"updates":[18],"across":[19],"layers":[20],"a":[22,198],"neural":[23],"network.":[24],"Prior":[25],"studies":[26],"have":[27],"explored":[28],"alternative":[29],"-":[30,36],"and,":[31],"some":[33],"cases,":[34],"simpler":[35],"mechanisms,":[38],"showing":[39],"that":[40,120,163,183],"they":[41],"can":[42,64,185],"sometimes":[43],"achieve":[44],"performance":[45,145],"similar":[46],"to":[47,68,78],"backpropagation.":[48,179],"However,":[49],"architectural":[51],"conditions":[52],"under":[53],"which":[54,58],"locally":[55],"optimized":[56],"networks,":[57,123,140],"avoid":[59],"end-to-end":[60,72,112,127,177],"error,":[63],"learn":[65],"representations":[66,157],"comparable":[67],"those":[69],"learned":[70],"through":[71],"remain":[74],"unclear.":[75],"We":[76,118],"aim":[77],"answer":[79],"this":[80],"question":[81],"context":[84],"self-supervised":[86,113],"an":[88],"important":[89],"framework":[90],"large-scale":[92],"pretraining":[93],"artificial":[95],"intelligence.":[96],"Here,":[97],"we":[98,141],"investigate":[99],"how":[100],"network":[101],"width":[102,184],"and":[103,111,137,191],"depth":[104],"affect":[105],"efficacy":[107],"greedy":[109,130,150],"layer-wise":[110,131,151],"convolutional":[116],"networks.":[117],"find":[119],"wider":[122],"benefits":[125],"over":[129],"shrink:":[133],"relatively":[135],"shallow":[136],"very":[138,164],"wide":[139,165],"even":[142],"observed":[143],"higher":[144],"models":[147],"trained":[148,176],"with":[149,178],"training.":[152],"Subsequent":[153],"analysis":[154],"formed":[158],"by":[159],"these":[160],"networks":[161,167,175],"shows":[162,182],"greedy-trained":[166],"exhibit":[168],"more":[169],"favorable":[170],"representational":[171,195],"geometry":[172,196],"than":[173],"do":[174],"This":[180],"work":[181],"compensate":[186],"restricted":[188],"credit":[189],"assignment":[190],"identifies":[192],"differences":[193],"as":[197],"potential":[199],"mechanism":[200],"their":[202],"improved":[203],"performance.":[204]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}