{"id":"https://openalex.org/W4386864749","doi":"https://doi.org/10.1145/3624476","title":"Surrogate Lagrangian Relaxation: A Path to Retrain-Free Deep Neural Network Pruning","display_name":"Surrogate Lagrangian Relaxation: A Path to Retrain-Free Deep Neural Network Pruning","publication_year":2023,"publication_date":"2023-09-19","ids":{"openalex":"https://openalex.org/W4386864749","doi":"https://doi.org/10.1145/3624476"},"language":"en","primary_location":{"id":"doi:10.1145/3624476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624476","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-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/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, USA"],"raw_orcid":"https://orcid.org/0000-0002-6409-7716","affiliations":[{"raw_affiliation_string":"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 A. Bragin","raw_affiliation_strings":["University of Connecticut, USA"],"raw_orcid":"https://orcid.org/0000-0002-7783-9053","affiliations":[{"raw_affiliation_string":"University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","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, USA"],"raw_orcid":"https://orcid.org/0000-0002-7691-3530","affiliations":[{"raw_affiliation_string":"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, USA"],"raw_orcid":"https://orcid.org/0000-0001-8862-9628","affiliations":[{"raw_affiliation_string":"University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","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, USA"],"raw_orcid":"https://orcid.org/0000-0003-0066-4379","affiliations":[{"raw_affiliation_string":"University of Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","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, USA"],"raw_orcid":"https://orcid.org/0000-0003-0891-1231","affiliations":[{"raw_affiliation_string":"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":0.2127,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49673607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"28","issue":"6","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9973000288009644,"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":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.8046830296516418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5368260741233826},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5262799859046936},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5104786157608032},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49719956517219543},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4708889126777649},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3708929419517517},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3655553460121155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046830296516418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368260741233826},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5262799859046936},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5104786157608032},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49719956517219543},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4708889126777649},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3708929419517517},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3655553460121155},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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:10.1145/3624476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624476","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G35862307","display_name":"CAREER: Distributionally Robust Learning, Control, and Benefits Analysis of Information Sharing for Connected and Autonomous Vehicles","funder_award_id":"2047354","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4146176377","display_name":null,"funder_award_id":"2022-67023-36399","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2012586594","https://openalex.org/W2076428552","https://openalex.org/W2163605009","https://openalex.org/W2164278908","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2602753196","https://openalex.org/W2748818695","https://openalex.org/W2771655537","https://openalex.org/W2805003733","https://openalex.org/W2896409484","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963145730","https://openalex.org/W2963163009","https://openalex.org/W2963363373","https://openalex.org/W2963828549","https://openalex.org/W2964233199","https://openalex.org/W2968296999","https://openalex.org/W2971275988","https://openalex.org/W2995492258","https://openalex.org/W2996874060","https://openalex.org/W3000865935","https://openalex.org/W3005842225","https://openalex.org/W3034513523","https://openalex.org/W3104849992","https://openalex.org/W3107407793","https://openalex.org/W3109790059","https://openalex.org/W3138516171","https://openalex.org/W3157506437","https://openalex.org/W3163145870","https://openalex.org/W3212348580","https://openalex.org/W4283366929","https://openalex.org/W4293584584","https://openalex.org/W4297848585","https://openalex.org/W4312201941","https://openalex.org/W4383905034","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6750227808","https://openalex.org/W6755843862","https://openalex.org/W6776147281"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Network":[0],"pruning":[1,268],"is":[2,52,86],"a":[3,40,178,192,270,274],"widely":[4],"used":[5],"technique":[6],"to":[7,54,104,110,223,245],"reduce":[8],"computation":[9],"cost":[10],"and":[11,26,80,127,144,156,163,171,204,237],"model":[12,77,254],"size":[13],"for":[14],"deep":[15],"neural":[16,146],"networks.":[17],"However,":[18],"the":[19,31,59,63,76,81,84,98,168,172,200,211,224,232,246,258,265,284],"typical":[20],"three-stage":[21,267],"pipeline":[22],"(i.e.,":[23],"training,":[24],"pruning,":[25],"retraining":[27,278],"(fine-tuning))":[28],"significantly":[29],"increases":[30],"overall":[32],"training":[33,99],"time.":[34],"In":[35],"this":[36],"article,":[37],"we":[38],"develop":[39],"systematic":[41],"weight-pruning":[42,64,188],"optimization":[43,189],"approach":[44,190,221,281],"based":[45,133,148],"on":[46,121,166,229],"surrogate":[47],"Lagrangian":[48],"relaxation":[49],"(SLR),":[50],"which":[51,263],"tailored":[53],"overcome":[55],"difficulties":[56],"caused":[57],"by":[58,88,95,113],"discrete":[60],"nature":[61],"of":[62,75,83,180,231,277],"problem.":[65],"We":[66,117,158],"further":[67],"prove":[68],"that":[69,185],"our":[70,119,186,219,250,280],"method":[71,120],"ensures":[72],"fast":[73],"convergence":[74,82],"compression":[78,194,213],"problem,":[79],"SLR":[85,96,220,240,251],"accelerated":[87],"using":[89,125,177],"quadratic":[90],"penalties.":[91],"Model":[92],"parameters":[93],"obtained":[94,112],"during":[97],"phase":[100],"are":[101],"much":[102],"closer":[103],"their":[105],"optimal":[106],"values":[107],"as":[108,136,141,151],"compared":[109],"those":[111],"other":[114],"state-of-the-art":[115,130,197],"methods.":[116],"evaluate":[118,160],"image":[122],"classification":[123,217],"tasks":[124,165],"CIFAR-10":[126],"ImageNet":[128],"with":[129],"multi-layer":[131],"perceptron":[132],"networks":[134,139],"such":[135,140,150],"MLP-Mixer;":[137],"attention-based":[138],"Swin":[142],"Transformer;":[143],"convolutional":[145],"network":[147],"models":[149],"VGG-16,":[152],"ResNet-18,":[153],"ResNet-50,":[154],"ResNet-110,":[155],"MobileNetV2.":[157],"also":[159,205,241],"object":[161,235],"detection":[162,175,236],"segmentation":[164,238],"COCO,":[167],"KITTI":[169],"benchmark,":[170],"TuSimple":[173],"lane":[174],"dataset":[176],"variety":[179],"models.":[181],"Experimental":[182],"results":[183],"demonstrate":[184],"SLR-based":[187],"achieves":[191,252],"higher":[193,208],"rate":[195,214],"than":[196],"methods":[198],"under":[199,210],"same":[201,212],"accuracy":[202,209,226,255],"requirement":[203],"can":[206],"achieve":[207],"requirement.":[215],"Under":[216,234],"tasks,":[218,239],"converges":[222,242],"desired":[225,247],"\u00d7":[227],"faster":[228,244],"both":[230],"datasets.":[233],"2\u00d7":[243],"accuracy.":[248,286],"Further,":[249],"high":[253],"even":[256],"at":[257],"hardpruning":[259],"stage":[260],"without":[261],"retraining,":[262],"reduces":[264],"traditional":[266],"into":[269],"two-stage":[271],"process.":[272],"Given":[273],"limited":[275],"budget":[276],"epochs,":[279],"quickly":[282],"recovers":[283],"model\u2019s":[285]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}