{"id":"https://openalex.org/W3035414321","doi":"https://doi.org/10.24963/ijcai.2020/387","title":"Is the Skip Connection Provable to Reform the Neural Network Loss Landscape?","display_name":"Is the Skip Connection Provable to Reform the Neural Network Loss Landscape?","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035414321","doi":"https://doi.org/10.24963/ijcai.2020/387","mag":"3035414321"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/387","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/387","pdf_url":"https://www.ijcai.org/proceedings/2020/0387.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0387.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076449077","display_name":"Lifu Wang","orcid":"https://orcid.org/0000-0002-3206-4928"},"institutions":[{"id":"https://openalex.org/I4210145478","display_name":"Beijing Municipal Education Commission","ror":"https://ror.org/04bpn6s66","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210145478"]},{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lifu Wang","raw_affiliation_strings":["Beijing Jiaotong University","Beijing Municipal Commission of Education Beijing Jiaotong University, Beijing, China","Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China Key Laboratory of Communication and Information Systems,"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Municipal Commission of Education Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I4210145478","https://openalex.org/I21193070"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China Key Laboratory of Communication and Information Systems,","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056603533","display_name":"Bo Shen","orcid":"https://orcid.org/0000-0003-3482-5783"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I4210145478","display_name":"Beijing Municipal Education Commission","ror":"https://ror.org/04bpn6s66","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210145478"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Shen","raw_affiliation_strings":["Beijing Jiaotong University","Beijing Municipal Commission of Education Beijing Jiaotong University, Beijing, China","Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China Key Laboratory of Communication and Information Systems,"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Municipal Commission of Education Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I4210145478","https://openalex.org/I21193070"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China Key Laboratory of Communication and Information Systems,","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101851953","display_name":"Ning Zhao","orcid":"https://orcid.org/0000-0003-1389-2469"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Zhao","raw_affiliation_strings":["Beijing Jiaotong University","Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China State Key Lab of Rail Traffic Control and Safety,","Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China State Key Lab of Rail Traffic Control and Safety,","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015455705","display_name":"Zhiyuan Zhang","orcid":"https://orcid.org/0000-0002-6752-0794"},"institutions":[{"id":"https://openalex.org/I4210145478","display_name":"Beijing Municipal Education Commission","ror":"https://ror.org/04bpn6s66","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210145478"]},{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhang","raw_affiliation_strings":["Beijing Jiaotong University","Beijing Municipal Commission of Education Beijing Jiaotong University, Beijing, China","Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China Key Laboratory of Communication and Information Systems,"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Municipal Commission of Education Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I4210145478","https://openalex.org/I21193070"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China Key Laboratory of Communication and Information Systems,","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076449077"],"corresponding_institution_ids":["https://openalex.org/I21193070","https://openalex.org/I4210145478"],"apc_list":null,"apc_paid":null,"fwci":0.5442,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73155196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2792","last_page":"2798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12676","display_name":"Machine Learning and ELM","score":0.9994999766349792,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.8836655616760254},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.7291408181190491},{"id":"https://openalex.org/keywords/social-connectedness","display_name":"Social connectedness","score":0.6880735158920288},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6576550006866455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6342429518699646},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.556442379951477},{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.5352455377578735},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.5324538350105286},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42155835032463074},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4176506996154785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3682146668434143},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2502480149269104},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09565052390098572}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.8836655616760254},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.7291408181190491},{"id":"https://openalex.org/C201943243","wikidata":"https://www.wikidata.org/wiki/Q7551008","display_name":"Social connectedness","level":2,"score":0.6880735158920288},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6576550006866455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6342429518699646},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.556442379951477},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.5352455377578735},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.5324538350105286},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42155835032463074},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4176506996154785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3682146668434143},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2502480149269104},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09565052390098572},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2020/387","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/387","pdf_url":"https://www.ijcai.org/proceedings/2020/0387.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/0f7a8ad9-e51f-4af7-9c6d-8dc8cc1a67bc","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/0f7a8ad9-e51f-4af7-9c6d-8dc8cc1a67bc","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, L, Shen, B, Zhao, N & Zhang, Z 2021, Is the skip connection provable to reform the neural network loss landscape? in C Bessiere (ed.), Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. IJCAI International Joint Conference on Artificial Intelligence, International Joint Conferences on Artificial Intelligence, pp. 2792-2798, 29th International Joint Conference on Artificial Intelligence, IJCAI 2020, Yokohama, Japan, 7/01/21. https://doi.org/10.24963/ijcai.2020/387","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/387","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/387","pdf_url":"https://www.ijcai.org/proceedings/2020/0387.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4802433577","display_name":null,"funder_award_id":"2018YFC0831300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4811743277","display_name":null,"funder_award_id":"2018YFC","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035414321.pdf","grobid_xml":"https://content.openalex.org/works/W3035414321.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W2163605009","https://openalex.org/W2166116275","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2541674938","https://openalex.org/W2563275261","https://openalex.org/W2590516361","https://openalex.org/W2600597492","https://openalex.org/W2750924312","https://openalex.org/W2758053331","https://openalex.org/W2777256551","https://openalex.org/W2777662428","https://openalex.org/W2788838181","https://openalex.org/W2789756211","https://openalex.org/W2793333878","https://openalex.org/W2797993462","https://openalex.org/W2950233433","https://openalex.org/W2951610569","https://openalex.org/W2951934643","https://openalex.org/W2962376003","https://openalex.org/W2962930448","https://openalex.org/W2963446085","https://openalex.org/W2963569411","https://openalex.org/W2963874210","https://openalex.org/W2963925364","https://openalex.org/W2964232029","https://openalex.org/W4200283578","https://openalex.org/W4288286305","https://openalex.org/W4293115691","https://openalex.org/W6631943919","https://openalex.org/W6743478991","https://openalex.org/W6791858558","https://openalex.org/W6803771590"],"related_works":["https://openalex.org/W2375684291","https://openalex.org/W3125761283","https://openalex.org/W2354676191","https://openalex.org/W3188646203","https://openalex.org/W2909957174","https://openalex.org/W4246278799","https://openalex.org/W136674370","https://openalex.org/W2164081328","https://openalex.org/W2105527480","https://openalex.org/W1986257383"],"abstract_inverted_index":{"The":[0,165],"residual":[1],"network":[2,33,77,124,132,160],"is":[3,64,88,177],"now":[4],"one":[5],"of":[6,30,73,85,104,108,129,142,156,167,190],"the":[7,16,21,28,31,38,44,48,68,70,74,82,100,105,121,126,130,140,143,153,178,188,191],"most":[8,173],"effective":[9],"structures":[10],"in":[11,194],"deep":[12,109,195],"learning,":[13],"which":[14],"utilizes":[15],"skip":[17,39,115,122,134,192],"connections":[18,40,135],"to":[19,98,138],"\u201cguarantee\"":[20],"performance":[22],"will":[23,161],"not":[24],"get":[25],"worse.":[26],"However,":[27],"non-convexity":[29],"neural":[32,111],"makes":[34],"it":[35,63],"unclear":[36],"whether":[37],"do":[41],"provably":[42],"improve":[43],"learning":[45],"ability":[46],"since":[47],"nonlinearity":[49],"may":[50],"create":[51],"many":[52],"local":[53,149,169],"minima.":[54],"In":[55,91],"some":[56,157],"previous":[57],"works":[58],"[Freeman":[59],"and":[60,117,133],"Bruna,":[61],"2016],":[62],"shown":[65],"that":[66,120,147],"despite":[67],"non-convexity,":[69],"loss":[71,106],"landscape":[72,107],"two-layer":[75,131,158],"ReLU":[76,110,159],"has":[78],"good":[79,127],"properties":[80,128],"when":[81],"number":[83],"m":[84],"hidden":[86],"nodes":[87],"very":[89,163],"large.":[90],"this":[92,96],"paper,":[93],"we":[94],"follow":[95],"line":[97],"study":[99],"topology":[101],"(sub-level":[102],"sets)":[103],"networks":[112],"with":[113],"a":[114,184],"connection":[116,123,193],"theoretically":[118],"prove":[119],"inherits":[125],"can":[136],"help":[137],"control":[139],"connectedness":[141],"sub-level":[144],"sets,":[145],"such":[146],"any":[148],"minima":[150,155,170],"worse":[151],"than":[152],"global":[154],"be":[162],"\u201cshallow\".":[164],"\u201cdepth\"":[166],"these":[168],"are":[171],"at":[172],"O(m^(\u03b7-1)/n),":[174],"where":[175],"n":[176],"input":[179],"dimension,":[180],"\u03b7<1.":[181],"This":[182],"provides":[183],"theoretical":[185],"explanation":[186],"for":[187],"effectiveness":[189],"learning.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}