{"id":"https://openalex.org/W3035888673","doi":"https://doi.org/10.23919/date48585.2020.9116535","title":"Probabilistic Sequential Multi-Objective Optimization of Convolutional Neural Networks","display_name":"Probabilistic Sequential Multi-Objective Optimization of Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3035888673","doi":"https://doi.org/10.23919/date48585.2020.9116535","mag":"3035888673"},"language":"en","primary_location":{"id":"doi:10.23919/date48585.2020.9116535","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5029544583","display_name":"Zixuan Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zixuan Yin","raw_affiliation_strings":["McGill University, Montreal"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091600002","display_name":"Warren J. Gross","orcid":"https://orcid.org/0000-0002-6226-6037"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Warren Gross","raw_affiliation_strings":["McGill University, Montreal"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034701871","display_name":"Brett H. Meyer","orcid":"https://orcid.org/0000-0002-6650-3298"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brett H. Meyer","raw_affiliation_strings":["McGill University, Montreal"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029544583"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67978715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1409 1556","issue":null,"first_page":"1055","last_page":"1060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/T12535","display_name":"Machine Learning and Data Classification","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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7680577039718628},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7285114526748657},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7004981637001038},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6663801670074463},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6386398673057556},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.6101858019828796},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.49661046266555786},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.49507084488868713},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4845494329929352},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4828363060951233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4769269824028015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47474342584609985},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4743179976940155},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3886300325393677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3318057060241699},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2691848874092102},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1327720582485199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680577039718628},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7285114526748657},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7004981637001038},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6663801670074463},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6386398673057556},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.6101858019828796},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.49661046266555786},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.49507084488868713},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4845494329929352},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4828363060951233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4769269824028015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47474342584609985},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4743179976940155},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3886300325393677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3318057060241699},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2691848874092102},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1327720582485199},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date48585.2020.9116535","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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":52,"referenced_works":["https://openalex.org/W60686164","https://openalex.org/W1522301498","https://openalex.org/W1558919105","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2097117768","https://openalex.org/W2106334424","https://openalex.org/W2112796928","https://openalex.org/W2117876524","https://openalex.org/W2156749117","https://openalex.org/W2194775991","https://openalex.org/W2335728318","https://openalex.org/W2534788641","https://openalex.org/W2553303224","https://openalex.org/W2554302513","https://openalex.org/W2594529350","https://openalex.org/W2612445135","https://openalex.org/W2748513770","https://openalex.org/W2773706593","https://openalex.org/W2808938483","https://openalex.org/W2888850958","https://openalex.org/W2890590696","https://openalex.org/W2913732044","https://openalex.org/W2949117887","https://openalex.org/W2949264490","https://openalex.org/W2962835968","https://openalex.org/W2963137684","https://openalex.org/W2963163009","https://openalex.org/W2963240979","https://openalex.org/W2963374479","https://openalex.org/W2963446712","https://openalex.org/W2963536136","https://openalex.org/W2963821229","https://openalex.org/W2963918968","https://openalex.org/W2964081807","https://openalex.org/W2964121744","https://openalex.org/W2964259004","https://openalex.org/W3118608800","https://openalex.org/W4297775537","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6682764186","https://openalex.org/W6703116779","https://openalex.org/W6729956949","https://openalex.org/W6730146958","https://openalex.org/W6734593296","https://openalex.org/W6737664043","https://openalex.org/W6743495212","https://openalex.org/W6756887525","https://openalex.org/W6759402224","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2735450835","https://openalex.org/W4233965824","https://openalex.org/W2607442583","https://openalex.org/W3199199693","https://openalex.org/W4286970057","https://openalex.org/W2967237190","https://openalex.org/W3028852288","https://openalex.org/W4323366554","https://openalex.org/W2405673391","https://openalex.org/W2200000192"],"abstract_inverted_index":{"With":[0,102],"the":[1,58,133],"advent":[2],"of":[3,54,60,98,128,136],"deeper,":[4],"larger":[5],"and":[6,111,132,170],"more":[7],"complex":[8],"convolutional":[9],"neural":[10],"networks":[11],"(CNN),":[12],"manual":[13],"design":[14],"has":[15],"become":[16],"a":[17,51,103,120,157],"daunting":[18],"task,":[19],"especially":[20],"when":[21],"hardware":[22],"performance":[23,59,79],"must":[24],"be":[25],"optimized.":[26],"Sequential":[27],"model-based":[28],"optimization":[29,37],"(SMBO)":[30],"is":[31],"an":[32],"efficient":[33,176],"method":[34,149],"for":[35],"hyperparameter":[36],"on":[38,67,95,150],"highly":[39],"parameterized":[40],"machine":[41],"learning":[42],"(ML)":[43],"algorithms,":[44],"able":[45],"to":[46,156],"find":[47],"good":[48],"configurations":[49],"with":[50,174],"limited":[52],"number":[53,135],"evaluations":[55],"by":[56],"predicting":[57],"candidates":[61,93],"before":[62],"evaluation.":[63],"A":[64],"case":[65],"study":[66],"MNIST":[68],"shows":[69],"that":[70,105,141,167,171],"SMBO":[71,161],"regression":[72],"model":[73],"prediction":[74,110],"error":[75,107],"significantly":[76],"impedes":[77],"search":[78],"in":[80,108,113,123,182],"multi-objective":[81],"optimization.":[82],"To":[83],"address":[84],"this":[85],"issue,":[86],"we":[87],"propose":[88],"probabilistic":[89,96,116,160],"SMBO,":[90],"which":[91],"selects":[92],"based":[94],"estimation":[97],"their":[99],"Pareto":[100,117,130,138,164],"efficiency.":[101],"formulation":[104],"incorporates":[106],"accuracy":[109],"uncertainty":[112],"latency":[114,184],"measurement,":[115],"efficiency":[118],"quantifies":[119],"candidate's":[121],"quality":[122],"two":[124],"ways:":[125],"its":[126],"likelihood":[127],"being":[129],"optimal,":[131],"expected":[134],"current":[137],"optimal":[139,165],"solutions":[140,166],"it":[142],"will":[143],"dominate.":[144],"We":[145],"evaluate":[146],"our":[147],"proposed":[148],"four":[151],"image":[152],"classification":[153],"problems.":[154],"Compared":[155],"deterministic":[158],"approach,":[159],"consistently":[162],"generates":[163],"perform":[168],"better,":[169],"are":[172],"competitive":[173],"state-of-the-art":[175],"CNN":[177],"models,":[178],"offering":[179],"tremendous":[180],"speedup":[181],"inference":[183],"while":[185],"maintaining":[186],"comparable":[187],"accuracy.":[188]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}