{"id":"https://openalex.org/W4308236550","doi":"https://doi.org/10.1109/icip46576.2022.9897767","title":"Truncated Lottery Ticket for Deep Pruning","display_name":"Truncated Lottery Ticket for Deep Pruning","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236550","doi":"https://doi.org/10.1109/icip46576.2022.9897767"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897767","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5084787837","display_name":"Iraj Saniee","orcid":"https://orcid.org/0000-0001-9162-9194"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iraj Saniee","raw_affiliation_strings":["Bell Labs,Nokia,Murray Hill,NJ,07974"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bell Labs,Nokia,Murray Hill,NJ,07974","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103087443","display_name":"Lisa Zhang","orcid":"https://orcid.org/0000-0001-6054-2176"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa Zhang","raw_affiliation_strings":["Bell Labs,Nokia,Murray Hill,NJ,07974"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bell Labs,Nokia,Murray Hill,NJ,07974","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088322413","display_name":"Bradley Magnetta","orcid":"https://orcid.org/0000-0001-5355-470X"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradley Magnetta","raw_affiliation_strings":["Yale University,Department of Applied Physics,New Haven,CT,06520"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Applied Physics,New Haven,CT,06520","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1849,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52249843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"606","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9990000128746033,"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":0.7358022332191467},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6635754704475403},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5647293925285339},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5127642750740051},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5041135549545288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46752217411994934},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4311748147010803},{"id":"https://openalex.org/keywords/lottery","display_name":"Lottery","score":0.43053358793258667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.429240345954895},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.4157010316848755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34617751836776733},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3413058817386627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21137180924415588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358022332191467},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6635754704475403},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5647293925285339},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5127642750740051},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5041135549545288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46752217411994934},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4311748147010803},{"id":"https://openalex.org/C2777340749","wikidata":"https://www.wikidata.org/wiki/Q6684955","display_name":"Lottery","level":2,"score":0.43053358793258667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.429240345954895},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.4157010316848755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34617751836776733},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3413058817386627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21137180924415588},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897767","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":33,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2134273960","https://openalex.org/W2147800946","https://openalex.org/W2618530766","https://openalex.org/W2766839578","https://openalex.org/W2786771851","https://openalex.org/W2787752464","https://openalex.org/W2901839763","https://openalex.org/W2915589364","https://openalex.org/W2964203871","https://openalex.org/W3080315965","https://openalex.org/W3103754749","https://openalex.org/W3104263050","https://openalex.org/W4205952419","https://openalex.org/W4287828539","https://openalex.org/W4289276774","https://openalex.org/W4292779060","https://openalex.org/W4394650770","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6679651198","https://openalex.org/W6745148473","https://openalex.org/W6745499037","https://openalex.org/W6751979845","https://openalex.org/W6755166560","https://openalex.org/W6755843862","https://openalex.org/W6759263581","https://openalex.org/W6768298127","https://openalex.org/W6774302960","https://openalex.org/W6780482815","https://openalex.org/W6995610602"],"related_works":["https://openalex.org/W2004731113","https://openalex.org/W1556639976","https://openalex.org/W2366147166","https://openalex.org/W2394167907","https://openalex.org/W2139765960","https://openalex.org/W2128949092","https://openalex.org/W2357035722","https://openalex.org/W2066997075","https://openalex.org/W2368351749","https://openalex.org/W2358800538"],"abstract_inverted_index":{"New":[0],"deep":[1,55,161],"learning":[2],"models":[3],"are":[4],"massively":[5],"over-parametrized,":[6],"e.g.,":[7],"GPT-3":[8],"and":[9,23,28,68,78,173,188,200],"Turing-NLG":[10],"exceed":[11,164],"100Bs":[12],"of":[13,53,62,90,111,123,126,147,168,178],"parameters.":[14],"Naturally,":[15],"model":[16],"reduction":[17],"techniques":[18],"such":[19],"as":[20],"pruning,":[21],"quantization,":[22],"distillation":[24],"have":[25],"been":[26],"proposed":[27,149,196],"deployed.":[29],"In":[30],"the":[31,34,41,50,71,74,124,145,148,165,176,195],"pruning":[32],"literature,":[33],"Lottery":[35],"Ticket":[36],"Hypothesis":[37],"(LTH)":[38],"is":[39,198],"amongst":[40],"most":[42],"cited.":[43],"LTH":[44,169],"provides":[45],"a":[46,54,59,102,108,115,127,140,190],"recipe":[47],"for":[48,184,193],"reducing":[49,186],"free":[51],"parameters":[52,82,112,125,133],"network":[56,192],"by":[57,65,157],"eliminating":[58],"large":[60],"fraction":[61],"its":[63],"edges":[64,72],"1)":[66],"remembering":[67],"reusing":[69],"only":[70],"on":[73],"highest-traffic":[75],"input-output":[76],"paths":[77],"2)":[79],"resetting":[80],"remaining":[81],"to":[83,113],"their":[84],"initial":[85],"values":[86],"after":[87],"each":[88],"round":[89],"elimination.":[91],"Here,":[92],"we":[93,131],"extend":[94],"this":[95],"idea":[96],"two":[97],"steps":[98],"further.":[99],"We":[100,143,163,181],"add":[101],"random":[103],"buildup":[104],"phase,":[105],"starting":[106],"from":[107],"small":[109],"percentage":[110],"reach":[114],"predefined":[116],"accuracy,":[117],"often":[118],"needing":[119],"fewer":[120],"than":[121],"50%":[122],"full":[128,179],"network.":[129],"Then":[130],"eliminate":[132],"using":[134,151],"an":[135],"LTH-like":[136],"procedure":[137],"combined":[138],"with":[139],"binary":[141],"search.":[142],"demonstrate":[144],"efficiency":[146],"technique":[150],"three":[152,159],"well-known":[153],"image":[154],"data":[155],"sets":[156],"sparsifying":[158],"standard":[160],"nets.":[162],"elimination":[166],"power":[167],"(over":[170],"98%":[171],"pruned)":[172],"effectively":[174],"match":[175],"performance":[177],"networks.":[180],"conclude":[182],"that":[183],"both":[185],"computation":[187],"maintaining":[189],"sparse":[191],"inference,":[194],"scheme":[197],"effective":[199],"practical.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}