{"id":"https://openalex.org/W3192404420","doi":"https://doi.org/10.24963/ijcai.2021/344","title":"Enabling Retrain-free Deep Neural Network Pruning Using Surrogate Lagrangian Relaxation","display_name":"Enabling Retrain-free Deep Neural Network Pruning Using Surrogate Lagrangian Relaxation","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3192404420","doi":"https://doi.org/10.24963/ijcai.2021/344","mag":"3192404420"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/344","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/344","pdf_url":"https://www.ijcai.org/proceedings/2021/0344.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0344.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002144478","display_name":"Deniz Gurevin","orcid":"https://orcid.org/0000-0002-7691-3530"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deniz Gurevin","raw_affiliation_strings":["University of Connecticut","Department of Electrical and Computer Engineering, University of Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023766412","display_name":"Mikhail A. Bragin","orcid":"https://orcid.org/0000-0002-7783-9053"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikhail Bragin","raw_affiliation_strings":["University of Connecticut","Department of Electrical and Computer Engineering, University of Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut","Department of Computer Science and Engineering, University of Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070625162","display_name":"Shanglin Zhou","orcid":"https://orcid.org/0000-0002-6409-7716"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanglin Zhou","raw_affiliation_strings":["University of Connecticut","Department of Computer Science and Engineering, University of Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041120549","display_name":"Lynn Pepin","orcid":"https://orcid.org/0000-0001-8862-9628"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lynn Pepin","raw_affiliation_strings":["University of Connecticut","Department of Computer Science and Engineering, University of Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375966","display_name":"Bingbing Li","orcid":"https://orcid.org/0000-0002-9224-2685"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingbing Li","raw_affiliation_strings":["University of Connecticut","Department of Computer Science and Engineering, University of Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004660487","display_name":"Fei Miao","orcid":"https://orcid.org/0000-0003-0066-4379"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Miao","raw_affiliation_strings":["University of Connecticut","Department of Computer Science and Engineering, University of Connecticut, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2497","last_page":"2504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976999759674072,"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":0.9926999807357788,"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/pruning","display_name":"Pruning","score":0.817108154296875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6630297899246216},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5645188689231873},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5448200702667236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310231447219849},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4515383541584015},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.45095646381378174},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44417697191238403},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.42387789487838745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3966684937477112},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3563983142375946},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.328291118144989},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2648371458053589},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25255903601646423}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.817108154296875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6630297899246216},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5645188689231873},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5448200702667236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310231447219849},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4515383541584015},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.45095646381378174},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44417697191238403},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42387789487838745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3966684937477112},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3563983142375946},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.328291118144989},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2648371458053589},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25255903601646423},{"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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/344","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/344","pdf_url":"https://www.ijcai.org/proceedings/2021/0344.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/344","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/344","pdf_url":"https://www.ijcai.org/proceedings/2021/0344.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3955272216","display_name":"A Revolutionary Way to Tackle Challenging MILP Problems in Power Systems through Accelerated Convergence, Formulation Tightening and Asynchronous Optimization","funder_award_id":"1810108","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7359047676","display_name":"S&AS: FND: COLLAB: Adaptable Vehicular Sensing and Control for Fleet-Oriented Systems in Smart Cities","funder_award_id":"1849246","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3192404420.pdf","grobid_xml":"https://content.openalex.org/works/W3192404420.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2012586594","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2554302513","https://openalex.org/W2748818695","https://openalex.org/W2751366252","https://openalex.org/W2768083806","https://openalex.org/W2798170643","https://openalex.org/W2805003733","https://openalex.org/W2896409484","https://openalex.org/W2924515500","https://openalex.org/W2949941638","https://openalex.org/W2952088488","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963145730","https://openalex.org/W2963163009","https://openalex.org/W2963828549","https://openalex.org/W2963981420","https://openalex.org/W2964233199","https://openalex.org/W2964266063","https://openalex.org/W2964282938","https://openalex.org/W2966256598","https://openalex.org/W2971275988","https://openalex.org/W3016413385","https://openalex.org/W3034818206","https://openalex.org/W3104849992","https://openalex.org/W3109790059","https://openalex.org/W4234117503","https://openalex.org/W4292363360","https://openalex.org/W4293584584"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Network":[0],"pruning":[1,25,174],"is":[2,52],"a":[3,40,159,178],"widely":[4],"used":[5],"technique":[6],"to":[7,54,94,100,175],"reduce":[8],"computation":[9],"cost":[10],"and":[11,26,118,129],"model":[12,161,189],"size":[13],"for":[14],"deep":[15],"neural":[16],"networks.":[17],"However,":[18],"the":[19,31,59,63,73,76,88,109,152,165,171,188],"typical":[20],"three-stage":[21,173],"pipeline,":[22],"i.e.,":[23],"training,":[24],"retraining":[27,169,182],"(fine-tuning)":[28],"significantly":[29],"increases":[30],"overall":[32],"training":[33,89],"trails.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"develop":[39],"systematic":[41],"weight-pruning":[42,64,142],"optimization":[43,143],"approach":[44,144,185],"based":[45],"on":[46,112],"Surrogate":[47],"Lagrangian":[48],"relaxation":[49],"(SLR),":[50],"which":[51],"tailored":[53],"overcome":[55],"difficulties":[56],"caused":[57],"by":[58,78,85,103],"discrete":[60],"nature":[61],"of":[62,75,181],"problem":[65],"while":[66],"ensuring":[67],"fast":[68],"convergence.":[69],"We":[70,107],"further":[71],"accelerate":[72],"convergence":[74],"SLR":[77,86],"using":[79,116,126,131],"quadratic":[80],"penalties.":[81],"Model":[82],"parameters":[83],"obtained":[84,102],"during":[87],"phase":[90],"are":[91],"much":[92],"closer":[93],"their":[95],"optimal":[96],"values":[97],"as":[98,120,122],"compared":[99],"those":[101],"other":[104],"state-of-the-art":[105],"methods.":[106],"evaluate":[108],"proposed":[110],"method":[111],"image":[113],"classification":[114],"tasks":[115,125],"CIFAR-10":[117],"ImageNet,":[119],"well":[121],"object":[123],"detection":[124,134],"COCO":[127],"2014":[128],"Ultra-Fast-Lane-Detection":[130],"TuSimple":[132],"lane":[133],"dataset.":[135],"Experimental":[136],"results":[137],"demonstrate":[138],"that":[139],"our":[140,184],"SLR-based":[141],"achieves":[145,158],"higher":[146],"compression":[147],"rate":[148],"than":[149],"state-of-the-arts":[150],"under":[151],"same":[153],"accuracy":[154,162],"requirement.":[155],"It":[156],"also":[157],"high":[160],"even":[163],"at":[164],"hard-pruning":[166],"stage":[167],"without":[168],"(reduces":[170],"traditional":[172],"two-stage).":[176],"Given":[177],"limited":[179],"budget":[180],"epochs,":[183],"quickly":[186],"recovers":[187],"accuracy.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}