{"id":"https://openalex.org/W4405055819","doi":"https://doi.org/10.1109/tetci.2024.3502463","title":"Convex-Concave Programming: An Effective Alternative for Optimizing Shallow Neural Networks","display_name":"Convex-Concave Programming: An Effective Alternative for Optimizing Shallow Neural Networks","publication_year":2024,"publication_date":"2024-12-05","ids":{"openalex":"https://openalex.org/W4405055819","doi":"https://doi.org/10.1109/tetci.2024.3502463"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2024.3502463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3502463","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-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/A5090915131","display_name":"Mohammad Askarizadeh","orcid":"https://orcid.org/0000-0002-5342-1824"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammad Askarizadeh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, &#x00C9;cole de Technologie Sup&#x00E9;rieure, University of Quebec, Montreal, QC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5342-1824","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, &#x00C9;cole de Technologie Sup&#x00E9;rieure, University of Quebec, Montreal, QC, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068477945","display_name":"Alireza Morsali","orcid":"https://orcid.org/0000-0002-8760-5218"},"institutions":[{"id":"https://openalex.org/I2802647910","display_name":"Burnaby Hospital","ror":"https://ror.org/00z6pvt32","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2802647910"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alireza Morsali","raw_affiliation_strings":["R&amp;D, Aibrary, Burnaby, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8760-5218","affiliations":[{"raw_affiliation_string":"R&amp;D, Aibrary, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I2802647910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043067916","display_name":"Sadegh Tofigh","orcid":"https://orcid.org/0000-0001-5622-1783"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sadegh Tofigh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, &#x00C9;cole de Technologie Sup&#x00E9;rieure, University of Quebec, Montreal, QC, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5622-1783","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, &#x00C9;cole de Technologie Sup&#x00E9;rieure, University of Quebec, Montreal, QC, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019659545","display_name":"Kim Khoa Nguyen","orcid":"https://orcid.org/0000-0002-9354-7544"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kim Khoa Nguyen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, &#x00C9;cole de Technologie Sup&#x00E9;rieure, University of Quebec, Montreal, QC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9354-7544","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, &#x00C9;cole de Technologie Sup&#x00E9;rieure, University of Quebec, Montreal, QC, Canada","institution_ids":["https://openalex.org/I159129438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.24523339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"4","first_page":"2894","last_page":"2907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8889999985694885,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8889999985694885,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.8702999949455261,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.8629999756813049,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/regular-polygon","display_name":"Regular polygon","score":0.5267485976219177},{"id":"https://openalex.org/keywords/concave-function","display_name":"Concave function","score":0.5260118246078491},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5045336484909058},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49851298332214355},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4978311061859131},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3490868806838989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24866124987602234},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.09338101744651794}],"concepts":[{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5267485976219177},{"id":"https://openalex.org/C66690126","wikidata":"https://www.wikidata.org/wiki/Q2914302","display_name":"Concave function","level":3,"score":0.5260118246078491},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5045336484909058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49851298332214355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4978311061859131},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3490868806838989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24866124987602234},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09338101744651794}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tetci.2024.3502463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3502463","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:espace2.etsmtl.ca:30328","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/30328/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"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":"Article publi\u00e9 dans une revue, r\u00e9vis\u00e9 par les pairs"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1440015328","https://openalex.org/W1530146942","https://openalex.org/W1966986674","https://openalex.org/W1988115241","https://openalex.org/W2044297353","https://openalex.org/W2086161653","https://openalex.org/W2095981367","https://openalex.org/W2103215959","https://openalex.org/W2112924664","https://openalex.org/W2113442785","https://openalex.org/W2124488712","https://openalex.org/W2141695047","https://openalex.org/W2199097987","https://openalex.org/W2221524898","https://openalex.org/W2513671774","https://openalex.org/W2743909828","https://openalex.org/W2963840269","https://openalex.org/W2997591727","https://openalex.org/W3011573842","https://openalex.org/W3036100489","https://openalex.org/W3125537303","https://openalex.org/W3134549107","https://openalex.org/W3153843575","https://openalex.org/W3203963792","https://openalex.org/W4206069576","https://openalex.org/W4210739128","https://openalex.org/W4212839235","https://openalex.org/W4220883578","https://openalex.org/W4236362309","https://openalex.org/W4249840661","https://openalex.org/W4250589301","https://openalex.org/W4379232471","https://openalex.org/W4387870594","https://openalex.org/W4390505997","https://openalex.org/W6631190155","https://openalex.org/W6637461557","https://openalex.org/W6675225614","https://openalex.org/W6677106874","https://openalex.org/W6681435938","https://openalex.org/W6681785522","https://openalex.org/W6682889407","https://openalex.org/W6684426766","https://openalex.org/W6696497002","https://openalex.org/W6727685206","https://openalex.org/W6737857923","https://openalex.org/W6738760171","https://openalex.org/W6756091659","https://openalex.org/W6756700207","https://openalex.org/W6764430539","https://openalex.org/W6767447093","https://openalex.org/W6774309501","https://openalex.org/W6778994361","https://openalex.org/W6787270125","https://openalex.org/W6795140394","https://openalex.org/W6839810613","https://openalex.org/W6849008447","https://openalex.org/W6867471781"],"related_works":["https://openalex.org/W2387950976","https://openalex.org/W2805356302","https://openalex.org/W2808215963","https://openalex.org/W1561462659","https://openalex.org/W4385714556","https://openalex.org/W2001828069","https://openalex.org/W4319661813","https://openalex.org/W3125304966","https://openalex.org/W154561153","https://openalex.org/W4389615602"],"abstract_inverted_index":{"In":[0,190],"this":[1],"study,":[2],"we":[3,41,70,225],"address":[4],"the":[5,16,32,60,64,76,138,176,215,242],"challenges":[6],"of":[7,18,26,63,102,111,129,244],"non-convex":[8],"optimization":[9,45],"in":[10,67,184],"neural":[11],"networks":[12],"(NNs)":[13],"by":[14,248],"formulating":[15],"training":[17],"multilayer":[19],"perceptron":[20],"(MLP)":[21],"NNs":[22],"as":[23,115,255],"a":[24,230,277],"difference":[25],"convex":[27,65,73],"functions":[28],"(DC)":[29],"problem.":[30],"Utilizing":[31],"basic":[33],"convex\u2013concave":[34],"algorithm":[35,196,210],"to":[36,95,146,175,214,221,229,237,251],"solve":[37],"our":[38,85,192,206,227,245,274],"DC":[39,68,77],"problems,":[40],"introduce":[42],"two":[43],"alternative":[44,279],"techniques,":[46],"<italic":[47,51,88,92,98,125,152,162,165,169,193,207,256,259,263],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[48,52,89,93,99,104,120,126,131,144,153,163,166,170,194,208,257,260,264],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DC-GD</i>":[49,90,209],"and":[50,91,168,205,262],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DC-OPT</i>,":[53,94],"for":[54,75,182,280],"determining":[55],"MLP":[56,283],"parameters.":[57],"By":[58],"leveraging":[59],"non-uniqueness":[61],"property":[62],"components":[66,74],"functions,":[69],"generate":[71],"strongly":[72],"NN":[78,159,232],"cost":[79],"function.":[80],"This":[81,135],"strong":[82],"convexity":[83],"enables":[84],"proposed":[86,246],"algorithms,":[87],"achieve":[96],"an":[97,124,186],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">iteration":[100,127],"complexity</i>":[101,128],"<inline-formula":[103,130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[105,132],"notation=\"LaTeX\">$O\\left(\\log":[106],"\\left(\\frac{1}{\\varepsilon":[107],"}\\right)\\right)$</tex-math></inline-formula>,":[108],"surpassing":[109],"that":[110,273],"other":[112,222],"solvers,":[113],"such":[114,254],"stochastic":[116],"gradient":[117],"descent":[118],"(<italic":[119,143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SGD</i>),":[121],"which":[122],"has":[123],"notation=\"LaTeX\">$O\\left(\\frac{1}{\\varepsilon":[133],"}\\right)$</tex-math></inline-formula>.":[134],"improvement":[136],"raises":[137],"convergence":[139],"rate":[140],"from":[141],"sublinear":[142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SGD</i>)":[145],"linear":[147],"(ours)":[148],"while":[149],"maintaining":[150],"comparable":[151,219],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">total":[154],"computational":[155,180],"costs</i>.":[156],"Furthermore,":[157],"conventional":[158,252],"optimizers":[160,253],"like":[161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SGD</i>,":[164,258],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">RMSprop</i>,":[167,261],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Adam</i>":[171,265],"are":[172],"highly":[173],"sensitive":[174,213],"learning":[177,188,203,216],"rate,":[178,217],"adding":[179],"overhead":[181],"practitioners":[183],"selecting":[185],"appropriate":[187],"rate.":[189],"contrast,":[191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DC-OPT</i>":[195],"is":[197,211,276],"hyperparameter-free":[198],"(i.e.,":[199],"it":[200],"requires":[201],"no":[202],"rate),":[204],"less":[212],"offering":[218],"accuracy":[220],"solvers.":[223],"Additionally,":[224],"extend":[226],"approach":[228,275],"convolutional":[231],"architecture,":[233],"demonstrating":[234],"its":[235],"applicability":[236],"modern":[238],"NNs.":[239,284],"We":[240],"evaluate":[241],"performance":[243],"algorithms":[247],"comparing":[249],"them":[250],"across":[266],"various":[267],"test":[268],"cases.":[269],"The":[270],"results":[271],"suggest":[272],"viable":[278],"optimizing":[281],"shallow":[282]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}