{"id":"https://openalex.org/W4297847336","doi":"https://doi.org/10.48550/arxiv.2209.07238","title":"Generalization Properties of NAS under Activation and Skip Connection Search","display_name":"Generalization Properties of NAS under Activation and Skip Connection Search","publication_year":2022,"publication_date":"2022-09-15","ids":{"openalex":"https://openalex.org/W4297847336","doi":"https://doi.org/10.48550/arxiv.2209.07238"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.07238","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.07238","pdf_url":"https://arxiv.org/pdf/2209.07238","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.07238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101559590","display_name":"Zhenyu Zhu","orcid":"https://orcid.org/0009-0007-2916-0461"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Zhenyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016703530","display_name":"Fanghui Liu","orcid":"https://orcid.org/0000-0003-4133-7921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Fanghui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004562735","display_name":"Grigorios G. Chrysos","orcid":"https://orcid.org/0000-0002-0650-1856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chrysos, Grigorios G","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027059837","display_name":"Volkan Cevher","orcid":"https://orcid.org/0000-0002-5004-201X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cevher, Volkan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101559590"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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":0.9970999956130981,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9951000213623047,"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/generalization","display_name":"Generalization","score":0.707705020904541},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.6822947263717651},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6319044828414917},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.6252073049545288},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.5872291922569275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5728483200073242},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4980754852294922},{"id":"https://openalex.org/keywords/tangent","display_name":"Tangent","score":0.4858560264110565},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4618130922317505},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.45611995458602905},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4184871017932892},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4176673889160156},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4137188792228699},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37526994943618774},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3704882562160492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35367709398269653},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.15459972620010376}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.707705020904541},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.6822947263717651},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6319044828414917},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.6252073049545288},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5872291922569275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5728483200073242},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4980754852294922},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.4858560264110565},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4618130922317505},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.45611995458602905},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4184871017932892},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4176673889160156},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4137188792228699},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37526994943618774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3704882562160492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35367709398269653},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.15459972620010376},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.07238","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.07238","pdf_url":"https://arxiv.org/pdf/2209.07238","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.07238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.07238","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.07238","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.07238","pdf_url":"https://arxiv.org/pdf/2209.07238","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3110577345","https://openalex.org/W2946235959","https://openalex.org/W587735977","https://openalex.org/W2902935192","https://openalex.org/W3134817226","https://openalex.org/W4318066384","https://openalex.org/W3215912596","https://openalex.org/W3198895633","https://openalex.org/W4385451479","https://openalex.org/W1978142926"],"abstract_inverted_index":{"Neural":[0,70],"Architecture":[1],"Search":[2],"(NAS)":[3],"has":[4,178],"fostered":[5],"the":[6,14,35,59,65,69,75,95,106,118,126,131,151,165,174,184,188],"automatic":[7],"discovery":[8],"of":[9,38,64,68,103,153,167,187,191],"state-of-the-art":[10],"neural":[11,91],"architectures.":[12],"Despite":[13],"progress":[15],"achieved":[16],"with":[17],"NAS,":[18],"so":[19],"far":[20],"there":[21],"is":[22,161],"little":[23],"attention":[24],"to":[25,98,124,136,164],"theoretical":[26],"guarantees":[27],"on":[28,141,150],"NAS.":[29,158],"In":[30],"this":[31,55],"work,":[32],"we":[33,57,112],"study":[34],"generalization":[36,100],"properties":[37],"NAS":[39,104,123],"under":[40,74,173],"a":[41,79,137],"unifying":[42,175],"framework":[43,176],"enabling":[44],"(deep)":[45],"layer":[46],"skip":[47],"connection":[48],"search":[49,81],"and":[50,89,114,170,177],"activation":[51,85,171],"function":[52],"search.":[53],"To":[54],"end,":[56],"derive":[58],"lower":[60,185],"(and":[61],"upper)":[62],"bounds":[63,102],"minimum":[66,96,189],"eigenvalue":[67,97,190],"Tangent":[71],"Kernel":[72],"(NTK)":[73],"(in)finite-width":[76],"regime":[77],"using":[78],"certain":[80],"space":[82],"including":[83],"mixed":[84],"functions,":[86],"fully":[87],"connected,":[88],"residual":[90],"networks.":[92],"We":[93],"use":[94],"establish":[99],"error":[101],"in":[105,130,182,193],"stochastic":[107],"gradient":[108],"descent":[109],"training.":[110],"Importantly,":[111],"theoretically":[113],"experimentally":[115],"show":[116],"how":[117],"derived":[119],"results":[120],"can":[121],"guide":[122],"select":[125],"top-performing":[127],"architectures,":[128],"even":[129],"case":[132],"without":[133],"training,":[134],"leading":[135],"train-free":[138],"algorithm":[139],"based":[140],"our":[142,145],"theory.":[143,196],"Accordingly,":[144],"numerical":[146],"validation":[147],"shed":[148],"light":[149],"design":[152],"computationally":[154],"efficient":[155],"methods":[156],"for":[157],"Our":[159],"analysis":[160],"non-trivial":[162],"due":[163],"coupling":[166],"various":[168],"architectures":[169],"functions":[172],"its":[179],"own":[180],"interest":[181],"providing":[183],"bound":[186],"NTK":[192],"deep":[194],"learning":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}