{"id":"https://openalex.org/W3091941622","doi":"https://doi.org/10.1109/dac18072.2020.9218518","title":"Convergence-Aware Neural Network Training","display_name":"Convergence-Aware Neural Network Training","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3091941622","doi":"https://doi.org/10.1109/dac18072.2020.9218518","mag":"3091941622"},"language":"en","primary_location":{"id":"doi:10.1109/dac18072.2020.9218518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5005702459","display_name":"Hyungjun Oh","orcid":"https://orcid.org/0009-0003-4058-7811"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungjun Oh","raw_affiliation_strings":["Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085503041","display_name":"Yongseung Yu","orcid":"https://orcid.org/0000-0001-9838-4310"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongseung Yu","raw_affiliation_strings":["Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051422135","display_name":"Giha Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Giha Ryu","raw_affiliation_strings":["Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028004870","display_name":"Gunjoo Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunjoo Ahn","raw_affiliation_strings":["Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101065774","display_name":"Yuri Jeong","orcid":"https://orcid.org/0009-0000-8195-0953"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yuri Jeong","raw_affiliation_strings":["Samsung Research, Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100657252","display_name":"Jiwon Seo","orcid":"https://orcid.org/0000-0002-4855-5609"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwon Seo","raw_affiliation_strings":["Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9977999925613403,"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/computation","display_name":"Computation","score":0.8375832438468933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7737263441085815},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.762286365032196},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6795337200164795},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.663093090057373},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6281077861785889},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4637008607387543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4608473479747772},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4479385316371918},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36965411901474},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3444746732711792}],"concepts":[{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.8375832438468933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737263441085815},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.762286365032196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6795337200164795},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.663093090057373},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6281077861785889},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4637008607387543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4608473479747772},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4479385316371918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36965411901474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3444746732711792},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac18072.2020.9218518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1978642402","https://openalex.org/W2045975556","https://openalex.org/W2109884165","https://openalex.org/W2112796928","https://openalex.org/W2163605009","https://openalex.org/W2335728318","https://openalex.org/W2402144811","https://openalex.org/W2469490737","https://openalex.org/W2513554817","https://openalex.org/W2606891064","https://openalex.org/W2611289746","https://openalex.org/W2618530766","https://openalex.org/W2769644379","https://openalex.org/W2774000609","https://openalex.org/W2785961331","https://openalex.org/W2896457183","https://openalex.org/W2963341956","https://openalex.org/W2963803379","https://openalex.org/W2964004663","https://openalex.org/W3101036738","https://openalex.org/W3118608800","https://openalex.org/W6676366587","https://openalex.org/W6703116779","https://openalex.org/W6713134421","https://openalex.org/W6720242923","https://openalex.org/W6738460352","https://openalex.org/W6746200960","https://openalex.org/W6746839373","https://openalex.org/W6748522178","https://openalex.org/W6755207826","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W2078379271","https://openalex.org/W2043460294","https://openalex.org/W4210712718","https://openalex.org/W1905398909"],"abstract_inverted_index":{"Training":[0],"a":[1,8,47,72,88],"deep":[2],"neural":[3],"network(DNN)":[4],"is":[5,18,26],"expensive,":[6],"requiring":[7],"large":[9],"amount":[10],"of":[11,49,90],"computation":[12,22,36,66,85],"time.":[13],"While":[14],"the":[15,41,60,78,83,110,117],"training":[16,25,118],"overhead":[17],"high,":[19],"not":[20],"all":[21],"in":[23,44,67,103],"DNN":[24,68,122],"equal.":[27],"Some":[28],"parameters":[29,50],"converge":[30],"faster":[31],"and":[32,114],"thus":[33],"their":[34,95],"gradient":[35,65,84],"may":[37,51],"contribute":[38],"little":[39],"to":[40,63,76],"parameter":[42,61,79],"update;":[43],"nearstationary":[45],"points":[46],"subset":[48],"change":[52],"very":[53],"little.":[54],"In":[55,107],"this":[56],"paper":[57],"we":[58,81],"exploit":[59],"convergence":[62,96],"optimize":[64],"training.":[69],"We":[70],"design":[71],"light-weight":[73],"monitoring":[74],"technique":[75],"track":[77],"convergence;":[80],"prune":[82],"stochastically":[86],"for":[87,120],"group":[89],"semantically":[91],"related":[92],"parameters,":[93],"exploiting":[94],"correlations.":[97],"These":[98],"techniques":[99,112],"are":[100],"efficiently":[101],"implemented":[102],"existing":[104],"GPU":[105],"kernels.":[106],"our":[108],"evaluation":[109],"optimization":[111],"substantially":[113],"robustly":[115],"improve":[116],"throughput":[119],"four":[121],"models":[123],"on":[124],"three":[125],"public":[126],"datasets.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}