{"id":"https://openalex.org/W4401513631","doi":"https://doi.org/10.1109/cec60901.2024.10611772","title":"Characterising Deep Learning Loss Landscapes with Local Optima Networks","display_name":"Characterising Deep Learning Loss Landscapes with Local Optima Networks","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4401513631","doi":"https://doi.org/10.1109/cec60901.2024.10611772"},"language":"en","primary_location":{"id":"doi:10.1109/cec60901.2024.10611772","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cec60901.2024.10611772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018877295","display_name":"Yuyang Zhou","orcid":"https://orcid.org/0000-0002-2188-2781"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuyang Zhou","raw_affiliation_strings":["School of Computer Science University of Nottingham Ningbo China,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science University of Nottingham Ningbo China,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063214931","display_name":"Ferrante Neri","orcid":"https://orcid.org/0000-0002-6100-6532"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ferrante Neri","raw_affiliation_strings":["School of Computer Science and Electronic Engineering University of Surrey,Guildford,United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering University of Surrey,Guildford,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046750599","display_name":"Ruibin Bai","orcid":"https://orcid.org/0000-0003-1722-568X"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibin Bai","raw_affiliation_strings":["School of Computer Science University of Nottingham Ningbo China,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science University of Nottingham Ningbo China,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018877295"],"corresponding_institution_ids":["https://openalex.org/I13591777"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.108594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T12676","display_name":"Machine Learning and ELM","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.6472165584564209},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.5668216347694397},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.519029974937439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49976634979248047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6472165584564209},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.5668216347694397},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.519029974937439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49976634979248047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec60901.2024.10611772","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cec60901.2024.10611772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G3427450249","display_name":null,"funder_award_id":"72071116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G707734207","display_name":null,"funder_award_id":"2022Z217,2023Z237","funder_id":"https://openalex.org/F4320324778","funder_display_name":"Ningbo Municipal Bureau of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324778","display_name":"Ningbo Municipal Bureau of Science and Technology","ror":"https://ror.org/00gskyj95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2007339694","https://openalex.org/W2009797711","https://openalex.org/W2112796928","https://openalex.org/W2161032864","https://openalex.org/W2194775991","https://openalex.org/W2559582155","https://openalex.org/W2750384547","https://openalex.org/W2766826419","https://openalex.org/W2887063112","https://openalex.org/W2959993166","https://openalex.org/W3011054152","https://openalex.org/W3015201913","https://openalex.org/W3123511746","https://openalex.org/W3129625903","https://openalex.org/W3181655383","https://openalex.org/W3208057219","https://openalex.org/W4282966553","https://openalex.org/W4285033151","https://openalex.org/W4287646898","https://openalex.org/W4312322700","https://openalex.org/W4318603207","https://openalex.org/W4377971424","https://openalex.org/W4382618754","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6735901087","https://openalex.org/W6783600611"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"Deep":[0],"learning":[1,30,103,140],"has":[2],"gained":[3],"significant":[4],"popularity":[5],"in":[6,63,153],"recent":[7,60],"years,":[8],"particularly":[9],"for":[10,198],"tasks":[11],"like":[12],"image":[13],"and":[14,20,129,136,149],"speech":[15],"recognition,":[16],"natural":[17],"language":[18],"processing,":[19],"other":[21],"intricate":[22],"pattern":[23],"recognition":[24],"challenges.":[25],"However,":[26],"training":[27,42],"a":[28,45,51,82],"deep":[29,139],"model":[31],"involves":[32],"tuning":[33],"millions":[34],"or":[35],"even":[36],"billions":[37],"of":[38,101,109,138,151,160,166,173,193],"parameters.":[39],"Consequently,":[40],"this":[41],"process":[43],"becomes":[44],"large-scale":[46],"optimisation":[47],"problem":[48],"associated":[49],"with":[50,75],"mostly":[52],"unknown":[53],"but":[54],"highly":[55],"non-convex":[56],"fitness":[57,64],"landscape.":[58],"In":[59,143],"decades,":[61],"advances":[62],"landscape":[65],"analysis":[66,114,135,186],"have":[67],"revolved":[68],"around":[69],"characterizing":[70],"landscapes":[71],"representing":[72],"loss":[73,141],"functions,":[74],"Local":[76],"Optima":[77],"Networks":[78],"(LONs)":[79],"emerging":[80],"as":[81],"promising":[83],"tool.":[84],"This":[85],"paper,":[86],"while":[87],"focusing":[88],"on":[89,116,127,163,189],"LeNet-5,":[90],"leverages":[91],"LON":[92,199],"to":[93,132],"address":[94],"four":[95],"key":[96],"questions":[97],"concerning":[98],"the":[99,102,107,113,120,134,147,154,158,161,164,167,171,181,190,194],"nature":[100,165],"problem.":[104],"We":[105],"emphasize":[106],"impact":[108,159],"experimental":[110],"conditions":[111],"during":[112],"phase":[115],"drawing":[117],"conclusions":[118,179],"about":[119,180],"problem's":[121,182],"nature.":[122],"The":[123],"results":[124],"shed":[125],"light":[126],"parametrization":[128],"optimiser":[130],"selection":[131],"enhance":[133],"comprehension":[137],"landscapes.":[142],"particular,":[144],"we":[145],"identify":[146],"presence":[148],"number":[150],"funnels":[152],"landscape's":[155],"structure,":[156],"study":[157],"dataset":[162],"problem,":[168],"investigate":[169],"how":[170],"choice":[172],"local":[174],"search":[175],"optimisers":[176],"may":[177],"influence":[178],"structure.":[183],"Finally,":[184],"sensitivity":[185],"was":[187],"conducted":[188],"perturbation":[191],"strength":[192],"Basin-Hopping":[195],"sampling":[196],"method":[197],"construction.":[200]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}