{"id":"https://openalex.org/W4415654885","doi":"https://doi.org/10.5220/0013696100004000","title":"A Convexity-Dependent Two-Phase Training Algorithm for Deep Neural Networks","display_name":"A Convexity-Dependent Two-Phase Training Algorithm for Deep Neural Networks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415654885","doi":"https://doi.org/10.5220/0013696100004000"},"language":null,"primary_location":{"id":"doi:10.5220/0013696100004000","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013696100004000","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013696100004000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048555215","display_name":"Tomas Hrycej","orcid":null},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tomas Hrycej","raw_affiliation_strings":["Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045444454","display_name":"Bernhard Bermeitinger","orcid":"https://orcid.org/0000-0002-2524-1850"},"institutions":[{"id":"https://openalex.org/I675453","display_name":"Vorarlberg University of Applied Sciences","ror":"https://ror.org/031wyx077","country_code":"AT","type":"education","lineage":["https://openalex.org/I675453"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bernhard Bermeitinger","raw_affiliation_strings":["Institute of Computer Science in Vorarlberg, University of St. Gallen (HSG), Dornbirn, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science in Vorarlberg, University of St. Gallen (HSG), Dornbirn, Austria","institution_ids":["https://openalex.org/I675453"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Massimo Pavone","orcid":null},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Massimo Pavone","raw_affiliation_strings":["Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"G\u00f6tz-Henrik Wiegand","orcid":null},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"G\u00f6tz-Henrik Wiegand","raw_affiliation_strings":["Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024322708","display_name":"Siegfried Handschuh","orcid":"https://orcid.org/0000-0002-6195-9034"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Siegfried Handschuh","raw_affiliation_strings":["Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of St.Gallen (HSG), St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27359682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9099000096321106,"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":0.9099000096321106,"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":0.010400000028312206,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.007300000172108412,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.7240999937057495},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.566100001335144},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5543000102043152},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.5357999801635742},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4284000098705292},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4242999851703644},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.39660000801086426},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.3853999972343445}],"concepts":[{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.7240999937057495},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5602999925613403},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5503000020980835},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.5357999801635742},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4902999997138977},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4242999851703644},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.3853999972343445},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34610000252723694},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C122268817","wikidata":"https://www.wikidata.org/wiki/Q2020318","display_name":"Frank\u2013Wolfe algorithm","level":5,"score":0.3046000003814697},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013696100004000","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013696100004000","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.25366","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.25366","pdf_url":"https://arxiv.org/pdf/2510.25366","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0013696100004000","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013696100004000","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,21,36,51,145],"key":[1],"task":[2],"of":[3,32,47],"machine":[4],"learning":[5],"is":[6,42,89,133,183],"to":[7,17,24,66,70,127,138,186,190],"minimize":[8],"the":[9,14,18,30,33,43,48,54,87,99,115,130,149,154,159,176],"loss":[10,34,49,55,118],"function":[11,56,88],"that":[12,53,117,178],"measures":[13],"model":[15],"fit":[16],"training":[19],"data.":[20],"numerical":[22],"methods":[23,72,96],"do":[25],"this":[26,92,179],"efficiently":[27],"depend":[28],"on":[29,158],"properties":[31,41],"function.":[35,50],"most":[37],"decisive":[38],"among":[39],"these":[40,162],"convexity":[44,128,181],"or":[45],"non-convexity":[46,126],"fact":[52],"can":[57],"have,":[58],"and":[59,166,194],"frequently":[60],"has,":[61],"non-convex":[62,71,164],"regions":[63],"has":[64],"led":[65],"a":[67,77,104,110,134],"widespread":[68],"commitment":[69],"such":[73,97],"as":[74,98],"Adam.":[75],"However,":[76],"local":[78],"minimum":[79],"implies":[80],"that,":[81],"in":[82,114,120],"some":[83],"environment":[84],"around":[85],"it,":[86],"convex.":[90],"In":[91,161],"environment,":[93],"second-order":[94],"minimizing":[95],"Conjugate":[100],"Gradient":[101],"(CG)":[102,168],"give":[103],"guaranteed":[105],"superlinear":[106],"convergence.":[107],"We":[108],"propose":[109],"novel":[111],"framework":[112],"grounded":[113],"hypothesis":[116,177],"functions":[119],"real-world":[121],"tasks":[122],"swap":[123,150],"from":[124],"initial":[125],"towards":[129],"optimum.":[131],"This":[132],"property":[135],"we":[136],"leverage":[137],"design":[139],"an":[140],"innovative":[141],"two-phase":[142],"optimization":[143],"algorithm.":[144],"presented":[146],"algorithm":[147],"detects":[148],"point":[151],"by":[152],"observing":[153],"gradient":[155],"norm":[156],"dependence":[157],"loss.":[160],"regions,":[163],"(Adam)":[165],"convex":[167],"algorithms":[169],"are":[170],"used,":[171],"respectively.":[172],"Computing":[173],"experiments":[174],"confirm":[175],"simple":[180],"structure":[182],"frequent":[184],"enough":[185],"be":[187],"practically":[188],"exploited":[189],"substantially":[191],"improve":[192],"convergence":[193],"accuracy.":[195]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-29T00:00:00"}