{"id":"https://openalex.org/W7155352875","doi":"https://doi.org/10.48550/arxiv.2604.20219","title":"Geometric Layer-wise Approximation Rates for Deep Networks","display_name":"Geometric Layer-wise Approximation Rates for Deep Networks","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155352875","doi":"https://doi.org/10.48550/arxiv.2604.20219"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.20219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20219","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.20219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134448669","display_name":"Shijun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Shijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134370621","display_name":"Zuowei Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Zuowei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134454932","display_name":"Yuesheng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yuesheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5134448669"],"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":0.9164000153541565,"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":0.9164000153541565,"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":0.03790000081062317,"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":0.010300000198185444,"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/residual","display_name":"Residual","score":0.6514000296592712},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.535099983215332},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.513700008392334},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49140000343322754},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.46050000190734863},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.3727000057697296},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3555000126361847}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6514000296592712},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5787000060081482},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49140000343322754},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4575999975204468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4499000012874603},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C114563136","wikidata":"https://www.wikidata.org/wiki/Q19725982","display_name":"Network planning and design","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2678999900817871}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.20219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20219","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.20219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20219","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Depth":[0],"is":[1,78,98,126,131],"widely":[2],"viewed":[3],"as":[4,140],"a":[5,44,51,58,141,152,167],"central":[6],"contributor":[7],"to":[8,82,119],"the":[9,26,31,83,93,103,109,120,156,163,176],"success":[10],"of":[11,33,63,96,106,162],"deep":[12,135],"neural":[13,17],"networks,":[14],"whereas":[15],"standard":[16],"network":[18,129],"approximation":[19,94],"theory":[20],"typically":[21],"provides":[22],"guarantees":[23],"only":[24],"for":[25,113],"final":[27],"output":[28],"and":[29,67],"leaves":[30],"role":[32],"intermediate":[34,75],"layers":[35],"largely":[36],"unclear.":[37],"We":[38],"address":[39],"this":[40],"gap":[41],"by":[42,100,133],"developing":[43],"quantitative":[45],"framework":[46],"in":[47],"which":[48],"depth":[49,71,138],"admits":[50],"precise":[52],"scale-dependent":[53],"interpretation.":[54],"Specifically,":[55],"we":[56],"design":[57,130],"single":[59],"shared":[60],"mixed-activation":[61],"architecture":[62,169],"fixed":[64],"width":[65],"$2dN+d+2$":[66],"any":[68],"prescribed":[69],"finite":[70],"such":[72],"that":[73,170],"each":[74,145],"readout":[76],"$\u03a6_\\ell$":[77,97],"itself":[79],"an":[80],"approximant":[81],"target":[84],"function":[85],"$f$.":[86],"For":[87],"$f\\in":[88],"L^p([0,1]^d)$":[89],"with":[90],"$p\\in":[91],"[1,\\infty)$,":[92],"error":[95],"controlled":[99],"$(2d+1)$":[101],"times":[102],"$L^p$":[104],"modulus":[105],"continuity":[107],"at":[108,151],"geometric":[110,121],"scale":[111,154],"$N^{-\\ell}$":[112],"all":[114],"$\\ell$.":[115],"The":[116],"estimate":[117],"reduces":[118],"rate":[122],"$(2d+1)N^{-\\ell}$":[123],"if":[124],"$f$":[125],"$1$-Lipschitz.":[127],"Our":[128],"inspired":[132],"multigrade":[134],"learning,":[136],"where":[137],"serves":[139],"progressive":[142],"refinement":[143,173],"mechanism:":[144],"new":[146],"correction":[147,158],"targets":[148],"residual":[149],"information":[150],"finer":[153],"while":[155],"earlier":[157],"terms":[159],"remain":[160],"part":[161],"later":[164],"readouts,":[165],"yielding":[166],"nested":[168],"supports":[171],"adaptive":[172],"without":[174],"redesigning":[175],"preceding":[177],"network.":[178]},"counts_by_year":[],"updated_date":"2026-04-24T06:07:52.864757","created_date":"2026-04-24T00:00:00"}