{"id":"https://openalex.org/W2963605649","doi":"https://doi.org/10.1609/aaai.v33i01.33015925","title":"Capacity Control of ReLU Neural Networks by Basis-Path Norm","display_name":"Capacity Control of ReLU Neural Networks by Basis-Path Norm","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963605649","doi":"https://doi.org/10.1609/aaai.v33i01.33015925","mag":"2963605649"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33015925","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015925","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4543/4421","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4543/4421","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051093347","display_name":"Shuxin Zheng","orcid":"https://orcid.org/0000-0001-7828-5374"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuxin Zheng","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101704281","display_name":"Qi Meng","orcid":"https://orcid.org/0000-0001-7082-6666"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qi Meng","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066928490","display_name":"Huishuai Zhang","orcid":"https://orcid.org/0000-0003-2711-7295"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huishuai Zhang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344549","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-1624-8492"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115592065","display_name":"Tie\u2010Yan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"5925","last_page":"5932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9983999729156494,"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/T12676","display_name":"Machine Learning and ELM","score":0.9983999729156494,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9939000010490417,"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/norm","display_name":"Norm (philosophy)","score":0.6237601041793823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5007810592651367},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.46801790595054626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44338977336883545},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43737146258354187},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41861778497695923},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4183812737464905},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35899317264556885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.281084269285202}],"concepts":[{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.6237601041793823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5007810592651367},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.46801790595054626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44338977336883545},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43737146258354187},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41861778497695923},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4183812737464905},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35899317264556885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.281084269285202},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33015925","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015925","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4543/4421","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4543","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33015925","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015925","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4543/4421","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8406824694","display_name":null,"funder_award_id":"U1636201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963605649.pdf","grobid_xml":"https://content.openalex.org/works/W2963605649.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W577198184","https://openalex.org/W639708223","https://openalex.org/W1720114023","https://openalex.org/W1836465849","https://openalex.org/W2127265926","https://openalex.org/W2133564696","https://openalex.org/W2156387975","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2401137308","https://openalex.org/W2533523411","https://openalex.org/W2533558946","https://openalex.org/W2579923771","https://openalex.org/W2605350416","https://openalex.org/W2613718673","https://openalex.org/W2613904329","https://openalex.org/W2709553318","https://openalex.org/W2732724430","https://openalex.org/W2756814140","https://openalex.org/W2897578533","https://openalex.org/W2950220847","https://openalex.org/W2950943852","https://openalex.org/W2963446712","https://openalex.org/W2963664410","https://openalex.org/W3118608800","https://openalex.org/W3137695714","https://openalex.org/W4295151786","https://openalex.org/W4297738147","https://openalex.org/W4310348270","https://openalex.org/W4385245566","https://openalex.org/W6637414576","https://openalex.org/W6682889407","https://openalex.org/W6687483927","https://openalex.org/W6725739302","https://openalex.org/W6740483536"],"related_works":["https://openalex.org/W2792268997","https://openalex.org/W4200352275","https://openalex.org/W2898900925","https://openalex.org/W2386387936","https://openalex.org/W2076794896","https://openalex.org/W3175461337","https://openalex.org/W4226319929","https://openalex.org/W3034021666","https://openalex.org/W1493495162","https://openalex.org/W1533959244"],"abstract_inverted_index":{"Recently,":[0],"path":[1,42,66,88,103,121,197],"norm":[2,43,67,89,104,167],"was":[3],"proposed":[4,242],"as":[5,68],"a":[6,123,130,156,165,172,189],"new":[7,166],"capacity":[8,59,99,181,213],"measure":[9,100,179],"for":[10],"neural":[11,52,183],"networks":[12,53,184,208],"with":[13,138],"Rectified":[14],"Linear":[15],"Unit":[16],"(ReLU)":[17],"activation":[18],"function,":[19,75],"which":[20,64,143,224],"takes":[21],"the":[22,34,41,45,50,69,73,87,91,98,110,146,150,180,203,226,231,241,250,254],"rescaling-invariant":[23],"property":[24],"of":[25,40,49,57,93,122,133,149,174,182,206],"ReLU":[26,51,124,207],"into":[27],"account.":[28],"It":[29,115],"has":[30],"been":[31,79],"shown":[32,80],"that":[33,56,119,145,240],"generalization":[35,47,84,147,190,204],"error":[36,191],"bound":[37,192],"in":[38],"terms":[39],"explains":[44,202],"empirical":[46,227],"behaviors":[48,205],"better":[54,83,247],"than":[55,211,253],"other":[58],"measures.":[60],"Moreover,":[61],"optimization":[62,222],"algorithms":[63,223],"take":[65],"regularization":[70,243,256],"term":[71],"to":[72,81,178],"loss":[74],"like":[76],"Path-SGD,":[77],"have":[78],"achieve":[82],"performance.":[85],"However,":[86],"counts":[90],"values":[92],"all":[94],"paths,":[95],"and":[96,140,199],"hence":[97],"based":[101,170,193],"on":[102,154,171,194,236,249],"could":[105],"be":[106,127],"improperly":[107],"influenced":[108],"by":[109,129,161,230],"dependency":[111],"among":[112],"different":[113],"paths.":[114,159],"is":[116],"also":[117],"known":[118],"each":[120],"network":[125,151],"can":[126],"represented":[128],"small":[131],"group":[132,173],"linearly":[134,175],"independent":[135,176],"basis":[136,158,196],"paths":[137,177],"multiplication":[139],"division":[141],"operation,":[142],"indicates":[144],"behavior":[148],"only":[152,155],"depends":[153],"few":[157],"Motivated":[160],"this,":[162],"we":[163,220],"propose":[164],"Basis-path":[168],"Norm":[169],"more":[185,209],"accurately.":[186],"We":[187],"establish":[188],"this":[195],"norm,":[198],"show":[200],"it":[201],"accurately":[210],"previous":[212,255],"measures":[214],"via":[215],"extensive":[216],"experiments.":[217],"In":[218],"addition,":[219],"develop":[221],"minimize":[225],"risk":[228],"regularized":[229],"basis-path":[232],"norm.":[233],"Our":[234],"experiments":[235],"benchmark":[237],"datasets":[238],"demonstrate":[239],"method":[244],"achieves":[245],"clearly":[246],"performance":[248],"test":[251],"set":[252],"approaches.":[257]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}