{"id":"https://openalex.org/W7223856830","doi":"https://doi.org/10.48550/arxiv.2610.33840","title":"Sliding Networks: A Family of Residual Structures Preserving Feature Learning and Feature Diversity","display_name":"Sliding Networks: A Family of Residual Structures Preserving Feature Learning and Feature Diversity","publication_year":2026,"publication_date":"2026-10-24","ids":{"openalex":"https://openalex.org/W7223856830","doi":"https://doi.org/10.48550/arxiv.2610.33840"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.33840","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33840","pdf_url":"https://arxiv.org/pdf/2610.33840","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2610.33840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138406375","display_name":"Datong Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Datong","raw_affiliation_strings":["Department of Neuroscience University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neuroscience University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039282308","display_name":"Blake Bordelon","orcid":"https://orcid.org/0000-0003-0455-9445","observed_orcids":["https://orcid.org/0000-0003-0455-9445"]},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210158291","display_name":"Laboratoire Jacques-Louis Lions","ror":"https://ror.org/04xmteb38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210141950","https://openalex.org/I4210158291"]},{"id":"https://openalex.org/I4387155306","display_name":"Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation","ror":"https://ror.org/02vnd0e65","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4387155306"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bordelon, Blake","raw_affiliation_strings":["Laboratoire Jacques-Louis Lions (LJLL) & Laboratoire de Probabilit\u00e9s ,","Statistique et Mod\u00e9lisation (LPSM) Sorbonne Universit\u00e9 Oden Institute and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Jacques-Louis Lions (LJLL) & Laboratoire de Probabilit\u00e9s ,","institution_ids":["https://openalex.org/I4210158291"]},{"raw_affiliation_string":"Statistique et Mod\u00e9lisation (LPSM) Sorbonne Universit\u00e9 Oden Institute and","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4387155306"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.30300000309944153,"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":0.30300000309944153,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2590000033378601,"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/T10320","display_name":"Neural Networks and Applications","score":0.21310000121593475,"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/resnet","display_name":"ResNet","score":0.7160000205039978},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.7179999947547913},{"id":"https://openalex.org/keywords/feature-diversity","display_name":"feature diversity","score":0.9990000128746033},{"id":"https://openalex.org/keywords/depth-scaling","display_name":"depth scaling","score":0.6200000047683716},{"id":"https://openalex.org/keywords/width-scaling","display_name":"width scaling","score":0.8949999809265137},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.47699999809265137},{"id":"https://openalex.org/keywords/scaling-laws","display_name":"scaling laws","score":0.5590000152587891},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7723000049591064},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7315000295639038},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6825000047683716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6439999938011169},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5383999943733215},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4758000075817108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.37229999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3677999973297119},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C24084028","wikidata":"https://www.wikidata.org/wiki/Q7429781","display_name":"Scaling limit","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C63548660","wikidata":"https://www.wikidata.org/wiki/Q858223","display_name":"Limit point","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2614000141620636}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.33840","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33840","pdf_url":"https://arxiv.org/pdf/2610.33840","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.33840","doi":"https://doi.org/10.48550/arxiv.2610.33840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.33840","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:arXiv.org:2610.33840","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33840","pdf_url":"https://arxiv.org/pdf/2610.33840","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/G1810770612","display_name":"MathInGreaterParis Fellowship Programme","funder_award_id":"101034255","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223856830.pdf","grobid_xml":"https://content.openalex.org/works/W7223856830.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2556364298","https://openalex.org/W2804589149","https://openalex.org/W2809090039","https://openalex.org/W2889237180","https://openalex.org/W2899663614","https://openalex.org/W2912322140","https://openalex.org/W2919115771","https://openalex.org/W2946609015","https://openalex.org/W2963095610","https://openalex.org/W2970971581","https://openalex.org/W3001279689","https://openalex.org/W3037932933","https://openalex.org/W3199241049","https://openalex.org/W4302011654","https://openalex.org/W4362515116","https://openalex.org/W4388979610","https://openalex.org/W4401043088","https://openalex.org/W4414595198","https://openalex.org/W4414846785","https://openalex.org/W4415798023","https://openalex.org/W7126086621","https://openalex.org/W7127887711","https://openalex.org/W7133225605","https://openalex.org/W7133243783"],"related_works":["https://openalex.org/W4415797066","https://openalex.org/W4282971804","https://openalex.org/W4387226075","https://openalex.org/W7223293282","https://openalex.org/W7126661406","https://openalex.org/W7127887711","https://openalex.org/W4416291078","https://openalex.org/W4416372146","https://openalex.org/W4414595198","https://openalex.org/W4319049797"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2],"tend":[3],"to":[4,36,126],"perform":[5],"best":[6],"at":[7,122,164],"large":[8],"widths":[9,31],"and":[10,32,39,57,90,117,143,154],"depths.":[11],"The":[12],"growing":[13],"interest":[14],"in":[15,19,34,64],"scaling":[16,28,78,178],"laws,":[17],"especially":[18],"the":[20,65,93,99,112],"language":[21],"modeling":[22],"domain,":[23],"has":[24],"motivated":[25],"procedures":[26],"for":[27,179],"up":[29],"network":[30],"depths":[33],"order":[35],"preserve":[37],"stability":[38],"computational":[40],"efficiency":[41],"of":[42,61],"training":[43],"dynamics.":[44],"Existing":[45],"depth-scaling":[46],"approaches":[47],"force":[48],"a":[49,59,76,172],"choice":[50],"between":[51,72,141],"retaining":[52],"locally":[53,131],"maximal":[54,132],"\\emph{feature":[55,62],"learning}":[56],"preserving":[58,146],"form":[60],"diversity}":[63],"residual":[66,84],"stream":[67],"arising":[68],"from":[69,177],"random":[70],"differences":[71,161],"channels.":[73],"We":[74],"examine":[75],"\\textit{joint":[77],"recipe}":[79],"that":[80],"preserves":[81],"both.":[82],"With":[83],"width":[85,88,142],"$N_\\flat$,":[86],"hidden":[87],"$N_\\sharp$,":[89],"depth":[91,144],"$L$,":[92],"key":[94],"quantity":[95],"is,":[96],"by":[97],"default,":[98],"limiting":[100],"ratio":[101],"$N_\\flat/(N_\\sharp":[102],"L)\\to\u03b1$,":[103],"while":[104,145],"correlated":[105],"initialization":[106],"(Half":[107],"Copy)":[108],"can":[109,137],"partially":[110],"relax":[111],"resulting":[113],"shape":[114],"constraints.":[115],"Theory":[116],"residual-MLP":[118],"experiments":[119,157],"support":[120],"convergence":[121],"fixed":[123,165],"positive":[124],"$\u03b1$":[125],"an":[127],"SDE":[128],"limit":[129,173],"with":[130],"feature":[133],"learning.":[134],"Hidden":[135],"computations":[136],"then":[138],"be":[139],"redistributed":[140],"this":[147],"limit,":[148],"like":[149],"turning":[150],"melody":[151],"into":[152],"harmony":[153],"back.":[155],"Language-model":[156],"nevertheless":[158],"show":[159],"performance":[160],"under":[162],"regrouping":[163],"parameter":[166],"count.":[167],"These":[168],"results":[169],"distinguish":[170],"approximating":[171],"(ODE":[174],"or":[175],"SDE)":[176],"better":[180],"performance.":[181]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-28T00:00:00"}