{"id":"https://openalex.org/W4285606915","doi":"https://doi.org/10.24963/ijcai.2022/246","title":"A Solver + Gradient Descent Training Algorithm for Deep Neural Networks","display_name":"A Solver + Gradient Descent Training Algorithm for Deep Neural Networks","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606915","doi":"https://doi.org/10.24963/ijcai.2022/246"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/246","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/246","pdf_url":"https://www.ijcai.org/proceedings/2022/0246.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0246.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031475293","display_name":"Dhananjay Ashok","orcid":"https://orcid.org/0000-0001-7500-3730"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Dhananjay Ashok","raw_affiliation_strings":["University of Toronto","University of Toronto,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto,","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043997113","display_name":"Vineel Nagisetty","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162562","display_name":"Borealis (Austria)","ror":"https://ror.org/05eat3g39","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210162562"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Vineel Nagisetty","raw_affiliation_strings":["Borealis AI","Borealis AI,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Borealis AI","institution_ids":["https://openalex.org/I4210162562"]},{"raw_affiliation_string":"Borealis AI,","institution_ids":["https://openalex.org/I4210162562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059606409","display_name":"Christopher Srinivasa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162562","display_name":"Borealis (Austria)","ror":"https://ror.org/05eat3g39","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210162562"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Christopher Srinivasa","raw_affiliation_strings":["Borealis AI","Borealis AI,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Borealis AI","institution_ids":["https://openalex.org/I4210162562"]},{"raw_affiliation_string":"Borealis AI,","institution_ids":["https://openalex.org/I4210162562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052292970","display_name":"Vijay Ganesh","orcid":"https://orcid.org/0000-0002-6029-2047"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vijay Ganesh","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031475293"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05544659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1766","last_page":"1773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":1.0,"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":0.9991000294685364,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9987999796867371,"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/maxima-and-minima","display_name":"Maxima and minima","score":0.8471877574920654},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.8048936128616333},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7964221239089966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.659810483455658},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6153731942176819},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5991688966751099},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5658254623413086},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5353249907493591},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.48902758955955505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.389962762594223},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3540750741958618},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2130623161792755}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.8471877574920654},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8048936128616333},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7964221239089966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.659810483455658},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6153731942176819},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5991688966751099},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5658254623413086},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5353249907493591},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.48902758955955505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.389962762594223},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3540750741958618},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2130623161792755},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/246","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/246","pdf_url":"https://www.ijcai.org/proceedings/2022/0246.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/246","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/246","pdf_url":"https://www.ijcai.org/proceedings/2022/0246.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5099999904632568,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606915.pdf","grobid_xml":"https://content.openalex.org/works/W4285606915.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2031279142","https://openalex.org/W2165698076","https://openalex.org/W2180612164","https://openalex.org/W2523246573","https://openalex.org/W2742801844","https://openalex.org/W2891698621","https://openalex.org/W2950183737","https://openalex.org/W2963600714","https://openalex.org/W2964810095","https://openalex.org/W2973514284","https://openalex.org/W2995896027","https://openalex.org/W2996098493","https://openalex.org/W3083971896","https://openalex.org/W4295312788","https://openalex.org/W4301187031","https://openalex.org/W4381683870"],"related_works":["https://openalex.org/W4315785049","https://openalex.org/W3015792155","https://openalex.org/W3118286710","https://openalex.org/W2115886818","https://openalex.org/W2937906318","https://openalex.org/W4225929918","https://openalex.org/W3095450733","https://openalex.org/W3118431319","https://openalex.org/W3004700632","https://openalex.org/W2466106906"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,20,58,75,89],"novel":[3],"hybrid":[4,50],"algorithm":[5],"for":[6,42,177],"training":[7,201],"Deep":[8],"Neural":[9],"Networks":[10],"that":[11,129,203],"combines":[12],"the":[13,92,96,105,112,189,200],"state-of-the-art":[14],"Gradient":[15],"Descent":[16],"(GD)":[17],"method":[18],"with":[19,104],"Mixed":[21],"Integer":[22],"Linear":[23],"Programming":[24],"(MILP)":[25],"solver,":[26],"outperforming":[27],"GD":[28,65,204],"and":[29,39,45,110,138,156,176,182],"variants":[30],"in":[31,74,150,172],"terms":[32,151],"of":[33,91,99,107,152,154,199],"accuracy,":[34],"as":[35,37,55,61],"well":[36,134],"resource":[38],"data":[40,137,157,202],"efficiency":[41],"both":[43],"regression":[44,160],"classification":[46,178],"tasks.":[47],"Our":[48],"GD+Solver":[49],"algorithm,":[51],"called":[52],"GDSolver,":[53],"works":[54],"follows:":[56],"given":[57],"DNN":[59],"D":[60,69],"input,":[62],"GDSolver":[63,81,130,162,184],"invokes":[64,82],"to":[66,86,135,187],"partially":[67],"train":[68],"until":[70,119],"it":[71],"gets":[72],"stuck":[73],"local":[76,113],"minima,":[77],"at":[78],"which":[79],"point":[80],"an":[83],"MILP":[84],"solver":[85],"exhaustively":[87],"search":[88],"region":[90],"loss":[93],"landscape":[94],"around":[95],"weight":[97],"assignments":[98],"D\u2019s":[100],"final":[101],"layer":[102],"parameters":[103],"goal":[106],"tunnelling":[108],"through":[109],"escaping":[111],"minima.":[114],"The":[115],"process":[116],"is":[117,122],"repeated":[118],"desired":[120],"accuracy":[121,191],"achieved.":[123],"In":[124],"our":[125],"experiments,":[126],"we":[127],"find":[128],"not":[131],"only":[132,197],"scales":[133],"additional":[136],"very":[139],"large":[140],"model":[141],"sizes,":[142],"but":[143],"also":[144],"outperforms":[145],"all":[146,193],"other":[147],"competing":[148,194],"methods":[149],"rates":[153],"convergence":[155],"efficiency.":[158],"For":[159],"tasks,":[161],"produced":[163],"models":[164],"that,":[165],"on":[166,180],"average,":[167],"had":[168],"31.5%":[169],"lower":[170],"MSE":[171],"48%":[173],"less":[174],"time,":[175],"tasks":[179],"MNIST":[181],"CIFAR10,":[183],"was":[185],"able":[186],"achieve":[188],"highest":[190],"over":[192],"methods,":[195],"using":[196],"50%":[198],"baselines":[205],"required.":[206]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}