{"id":"https://openalex.org/W2808687583","doi":"https://doi.org/10.1137/19m1246468","title":"Fast Convex Pruning of Deep Neural Networks","display_name":"Fast Convex Pruning of Deep Neural Networks","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2808687583","doi":"https://doi.org/10.1137/19m1246468","mag":"2808687583"},"language":"en","primary_location":{"id":"doi:10.1137/19m1246468","is_oa":true,"landing_page_url":"https://doi.org/10.1137/19m1246468","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1246468","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1246468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060271129","display_name":"Alireza Aghasi","orcid":"https://orcid.org/0000-0002-9534-2024"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alireza Aghasi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005771765","display_name":"Afshin Abdi","orcid":"https://orcid.org/0000-0002-2038-4772"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Afshin Abdi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041443633","display_name":"Justin Romberg","orcid":"https://orcid.org/0000-0002-6616-197X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Justin Romberg","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060271129"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1796,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.42366116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":"1","first_page":"158","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9984999895095825,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9983000159263611,"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/trim","display_name":"Trim","score":0.9313298463821411},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.720392644405365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6482747793197632},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5808770656585693},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5193892121315002},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5049617886543274},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.49018603563308716},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.4750385582447052},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46388962864875793},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4487876892089844},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4437953233718872},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4386236369609833},{"id":"https://openalex.org/keywords/lasso","display_name":"Lasso (programming language)","score":0.4132593274116516},{"id":"https://openalex.org/keywords/convex-combination","display_name":"Convex combination","score":0.4112570285797119},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.3977675139904022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32413238286972046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25641828775405884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17980355024337769}],"concepts":[{"id":"https://openalex.org/C88611116","wikidata":"https://www.wikidata.org/wiki/Q957004","display_name":"Trim","level":2,"score":0.9313298463821411},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.720392644405365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6482747793197632},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5808770656585693},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5193892121315002},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5049617886543274},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.49018603563308716},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.4750385582447052},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46388962864875793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4487876892089844},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4437953233718872},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4386236369609833},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.4132593274116516},{"id":"https://openalex.org/C111110010","wikidata":"https://www.wikidata.org/wiki/Q2627315","display_name":"Convex combination","level":4,"score":0.4112570285797119},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.3977675139904022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32413238286972046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25641828775405884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17980355024337769},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1137/19m1246468","is_oa":true,"landing_page_url":"https://doi.org/10.1137/19m1246468","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1246468","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1806.06457","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.06457","pdf_url":"https://arxiv.org/pdf/1806.06457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":null},{"id":"mag:2808687583","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.06457.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1806.06457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.06457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1137/19m1246468","is_oa":true,"landing_page_url":"https://doi.org/10.1137/19m1246468","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1246468","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808687583.pdf","grobid_xml":"https://content.openalex.org/works/W2808687583.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1509689762","https://openalex.org/W1684009677","https://openalex.org/W1981025032","https://openalex.org/W2015418199","https://openalex.org/W2025223969","https://openalex.org/W2047028564","https://openalex.org/W2052044664","https://openalex.org/W2076063813","https://openalex.org/W2090405809","https://openalex.org/W2095705004","https://openalex.org/W2112796928","https://openalex.org/W2135046866","https://openalex.org/W2137198385","https://openalex.org/W2156297475","https://openalex.org/W2163605009","https://openalex.org/W2164278908","https://openalex.org/W2164452299","https://openalex.org/W2172166488","https://openalex.org/W2286188813","https://openalex.org/W2557283755","https://openalex.org/W2590106345","https://openalex.org/W2949117887","https://openalex.org/W2962896218","https://openalex.org/W2962963202","https://openalex.org/W2963441888","https://openalex.org/W2963674932","https://openalex.org/W2965497096","https://openalex.org/W3104501706","https://openalex.org/W3124617746","https://openalex.org/W4234698323","https://openalex.org/W4292363360"],"related_works":["https://openalex.org/W2996319422","https://openalex.org/W3056296174","https://openalex.org/W3045135238","https://openalex.org/W3022018744","https://openalex.org/W3186053734","https://openalex.org/W2806802250","https://openalex.org/W2993419428","https://openalex.org/W2952007262","https://openalex.org/W2948103995","https://openalex.org/W131197043","https://openalex.org/W3010631141","https://openalex.org/W2746283391","https://openalex.org/W416513604","https://openalex.org/W2135144664","https://openalex.org/W2125675358","https://openalex.org/W2986486878","https://openalex.org/W3119491467","https://openalex.org/W2803224311","https://openalex.org/W2951051440","https://openalex.org/W1961876782"],"abstract_inverted_index":{"We":[0,35],"develop":[1],"a":[2,10,17,24,37,52,76,89,99,186],"fast,":[3,53],"tractable":[4],"technique":[5],"called":[6],"Net-Trim":[7,41,72,192],"for":[8,141,193],"simplifying":[9],"trained":[11,25],"neural":[12],"network.":[13],"The":[14],"method":[15,180],"is":[16,98,130],"convex":[18,55,167],"postprocessing":[19],"module,":[20],"which":[21,184],"prunes":[22],"(sparsifies)":[23],"network":[26,90,194],"layer":[27,91,113,117],"by":[28],"layer,":[29],"while":[30],"preserving":[31],"the":[32,44,64,81,112,116,131,145,153,162,177],"internal":[33],"responses.":[34],"present":[36],"comprehensive":[38],"analysis":[39,59,149],"of":[40,83,101,152,164,181,191],"from":[42,115,124],"both":[43],"algorithmic":[45,173],"and":[46,66,70,74,147,166,188,196],"sample":[47,77],"complexity":[48,78],"standpoints,":[49],"centered":[50],"on":[51,80,161,176],"scalable":[54],"optimization":[56],"program.":[57],"Our":[58],"includes":[60],"consistency":[61],"results":[62,136,160],"between":[63],"initial":[65],"retrained":[67],"models":[68],"before":[69],"after":[71],"application":[73],"provides":[75],"bound":[79],"number":[82],"input":[84,132],"samples":[85],"needed":[86],"to":[87,139],"discover":[88],"with":[92],"sparse":[93,142],"topology.":[94],"Specifically,":[95],"if":[96],"there":[97],"set":[100],"weights":[102,123],"that":[103,109],"uses":[104,150],"at":[105],"most":[106],"$s$":[107],"terms":[108],"can":[110,120],"recreate":[111],"outputs":[114],"inputs,":[118],"we":[119,170],"find":[121],"these":[122],"$\\mathcal{O}(s\\log":[125],"N/s)$":[126],"samples,":[127],"where":[128],"$N$":[129],"size.":[133],"These":[134],"theoretical":[135],"are":[137],"similar":[138],"those":[140],"regression":[143],"using":[144],"Lasso,":[146],"our":[148],"some":[151],"same":[154],"recently":[155],"developed":[156],"tools":[157],"(namely":[158],"recent":[159],"concentration":[163],"measure":[165],"analysis).":[168],"Finally,":[169],"propose":[171],"an":[172],"framework":[174],"based":[175],"alternating":[178],"direction":[179],"multipliers":[182],"(ADMM),":[183],"allows":[185],"fast":[187],"simple":[189],"implementation":[190],"pruning":[195],"compression.":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}