{"id":"https://openalex.org/W3212339248","doi":"https://doi.org/10.1109/icc45855.2022.9838754","title":"DNN gradient lossless compression: Can GenNorm be the answer?","display_name":"DNN gradient lossless compression: Can GenNorm be the answer?","publication_year":2022,"publication_date":"2022-05-16","ids":{"openalex":"https://openalex.org/W3212339248","doi":"https://doi.org/10.1109/icc45855.2022.9838754","mag":"3212339248"},"language":"en","primary_location":{"id":"doi:10.1109/icc45855.2022.9838754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45855.2022.9838754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2022 - IEEE International Conference on Communications","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/A5076333348","display_name":"Zhong-Jing Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong-Jing Chen","raw_affiliation_strings":["NYCU,Taiwan","NYCU, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYCU,Taiwan","institution_ids":[]},{"raw_affiliation_string":"NYCU, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082162206","display_name":"Eduin E. Hernandez","orcid":"https://orcid.org/0009-0008-2812-5311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eduin E. Hernandez","raw_affiliation_strings":["NYCU,Taiwan","NYCU, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYCU,Taiwan","institution_ids":[]},{"raw_affiliation_string":"NYCU, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082244371","display_name":"Yu-Chih Huang","orcid":"https://orcid.org/0000-0003-2135-1232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Chih Huang","raw_affiliation_strings":["NYCU,Taiwan","NYCU, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYCU,Taiwan","institution_ids":[]},{"raw_affiliation_string":"NYCU, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067224441","display_name":"Stefano Rini","orcid":"https://orcid.org/0000-0003-1681-3316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefano Rini","raw_affiliation_strings":["NYCU,Taiwan","NYCU, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYCU,Taiwan","institution_ids":[]},{"raw_affiliation_string":"NYCU, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3495,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82460242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9980000257492065,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9980000257492065,"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":0.9980000257492065,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9966999888420105,"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/lossless-compression","display_name":"Lossless compression","score":0.8533443808555603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261539101600647},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.605044960975647},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.5584990978240967},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.511050820350647},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5048874020576477},{"id":"https://openalex.org/keywords/laplace-distribution","display_name":"Laplace distribution","score":0.4568191170692444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3617936074733734},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3217487931251526},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.30335864424705505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24132278561592102},{"id":"https://openalex.org/keywords/laplace-transform","display_name":"Laplace transform","score":0.177261084318161},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07122763991355896}],"concepts":[{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.8533443808555603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261539101600647},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.605044960975647},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5584990978240967},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.511050820350647},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5048874020576477},{"id":"https://openalex.org/C183057437","wikidata":"https://www.wikidata.org/wiki/Q671617","display_name":"Laplace distribution","level":3,"score":0.4568191170692444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617936074733734},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3217487931251526},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.30335864424705505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24132278561592102},{"id":"https://openalex.org/C97937538","wikidata":"https://www.wikidata.org/wiki/Q199691","display_name":"Laplace transform","level":2,"score":0.177261084318161},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07122763991355896},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc45855.2022.9838754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45855.2022.9838754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2022 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1994520254","https://openalex.org/W2122962290","https://openalex.org/W2302255633","https://openalex.org/W2407022425","https://openalex.org/W2478708596","https://openalex.org/W2535838896","https://openalex.org/W2913010492","https://openalex.org/W2963095610","https://openalex.org/W2963446712","https://openalex.org/W2963766684","https://openalex.org/W2964081807","https://openalex.org/W2970821029","https://openalex.org/W2990352720","https://openalex.org/W3010825589","https://openalex.org/W3081178085","https://openalex.org/W3103802018","https://openalex.org/W3158434734","https://openalex.org/W3169848021","https://openalex.org/W4288022516","https://openalex.org/W4297687186","https://openalex.org/W6698183232","https://openalex.org/W6714239094","https://openalex.org/W6725739302","https://openalex.org/W6754341472","https://openalex.org/W6758728975","https://openalex.org/W6767032739","https://openalex.org/W6770275949","https://openalex.org/W6770895831","https://openalex.org/W6786061324"],"related_works":["https://openalex.org/W1680283075","https://openalex.org/W3080614128","https://openalex.org/W2380116549","https://openalex.org/W3202870363","https://openalex.org/W4239869440","https://openalex.org/W2314401560","https://openalex.org/W821232595","https://openalex.org/W2071805648","https://openalex.org/W2409003266","https://openalex.org/W4200128017"],"abstract_inverted_index":{"In":[0,55,121],"this":[1,122,170],"paper,":[2],"the":[3,29,44,60,75,82,114,133,154,164,182,196],"problem":[4],"of":[5,77,130,163,178,181],"optimal":[6],"gradient":[7,62,83,91,109,134,166,198],"lossless":[8,67,179,188],"compression":[9,19,68,180,207],"in":[10,22,36,118,176,220],"Deep":[11],"Neural":[12],"Network":[13],"(DNN)":[14],"training":[15,26,223],"is":[16,20,64],"considered.":[17],"Gradient":[18],"relevant":[21],"many":[23],"distributed":[24,56,221],"DNN":[25,57,165,222],"scenarios,":[27],"including":[28],"recently":[30],"popular":[31],"federated":[32],"learning":[33],"(FL)":[34],"scenario":[35],"which":[37],"each":[38],"remote":[39],"users":[40],"are":[41],"connected":[42],"to":[43,73,106,151,195],"parameter":[45],"server":[46],"(PS)":[47],"through":[48],"a":[49,111,142,159],"noiseless":[50],"but":[51],"rate":[52],"limited":[53],"channel.":[54],"training,":[58],"if":[59],"underlying":[61],"distribution":[63,112,117],"available,":[65],"classical":[66,186],"approaches":[69],"can":[70,93,103,136],"be":[71,94,104,137],"used":[72,105],"reduce":[74],"number":[76],"bits":[78],"required":[79],"for":[80,127],"communicating":[81],"entries.":[84],"Mean":[85],"field":[86],"analysis":[87],"has":[88,110,216],"suggested":[89],"that":[90,108,153,215],"updates":[92],"considered":[95],"as":[96,140,192],"independent":[97],"random":[98],"variables,":[99],"while":[100],"Laplace":[101],"approximation":[102],"argue":[107,125],"approximating":[113],"normal":[115,144],"(Norm)":[116],"some":[119,128],"regimes.":[120],"paper":[123],"we":[124],"that,":[126],"networks":[129],"practical":[131,218],"interest,":[132],"entries":[135],"well":[138],"modelled":[139],"having":[141],"generalized":[143],"(GenNorm)":[145],"distribution.":[146,168],"We":[147],"provide":[148],"numerical":[149],"evaluations":[150],"validate":[152],"hypothesis":[155],"GenNorm":[156],"modelling":[157],"provides":[158,173,204],"more":[160],"accurate":[161],"prediction":[162],"tail":[167],"Additionally,":[169],"modeling":[171],"choice":[172],"concrete":[174],"improvement":[175],"terms":[177],"gradients":[183],"when":[184],"applying":[185],"fix-to-variable":[187],"coding":[189],"algorithms,":[190],"such":[191],"Huffman":[193],"coding,":[194],"quantized":[197],"updates.":[199],"This":[200],"latter":[201],"results":[202],"indeed":[203],"an":[205],"effective":[206],"strategy":[208],"with":[209],"low":[210],"memory":[211],"and":[212],"computational":[213],"complexity":[214],"great":[217],"relevance":[219],"scenarios.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}