{"id":"https://openalex.org/W4206119629","doi":"https://doi.org/10.1109/ipccc51483.2021.9679419","title":"Communication-Efficient Quantized SGD for Learning Polynomial Neural Network","display_name":"Communication-Efficient Quantized SGD for Learning Polynomial Neural Network","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W4206119629","doi":"https://doi.org/10.1109/ipccc51483.2021.9679419"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc51483.2021.9679419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc51483.2021.9679419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)","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/A5048892464","display_name":"Zhanpeng Yang","orcid":"https://orcid.org/0000-0002-3656-9085"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanpeng Yang","raw_affiliation_strings":["ShanghaiTech University,School of Information Science and Technology,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041989556","display_name":"Yong Zhou","orcid":"https://orcid.org/0000-0002-7499-6256"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhou","raw_affiliation_strings":["ShanghaiTech University,School of Information Science and Technology,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053320672","display_name":"Youlong Wu","orcid":"https://orcid.org/0000-0002-4383-9995"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youlong Wu","raw_affiliation_strings":["ShanghaiTech University,School of Information Science and Technology,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022499594","display_name":"Yuanming Shi","orcid":"https://orcid.org/0000-0002-1418-7465"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanming Shi","raw_affiliation_strings":["ShanghaiTech University,School of Information Science and Technology,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9987999796867371,"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":0.9984999895095825,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.817886233329773},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.708519697189331},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.659082293510437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6495254039764404},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5799964070320129},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5344637632369995},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.47689464688301086},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.47685468196868896},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44105881452560425},{"id":"https://openalex.org/keywords/quadratic-function","display_name":"Quadratic function","score":0.4389270544052124},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41410937905311584},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.3834023177623749},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2807047665119171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16569775342941284}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.817886233329773},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.708519697189331},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.659082293510437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6495254039764404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5799964070320129},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5344637632369995},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.47689464688301086},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47685468196868896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44105881452560425},{"id":"https://openalex.org/C166437778","wikidata":"https://www.wikidata.org/wiki/Q50695","display_name":"Quadratic function","level":3,"score":0.4389270544052124},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41410937905311584},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3834023177623749},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2807047665119171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16569775342941284},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc51483.2021.9679419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc51483.2021.9679419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2133564696","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2617766261","https://openalex.org/W2769644379","https://openalex.org/W2798291370","https://openalex.org/W2887509927","https://openalex.org/W2887611796","https://openalex.org/W2936060459","https://openalex.org/W2963417959","https://openalex.org/W2963759574","https://openalex.org/W2964031251","https://openalex.org/W2964256664","https://openalex.org/W2969519626","https://openalex.org/W2975491454","https://openalex.org/W2975778934","https://openalex.org/W2999074226","https://openalex.org/W3003771358","https://openalex.org/W3041971333","https://openalex.org/W3088898206","https://openalex.org/W3188102017","https://openalex.org/W3202461677","https://openalex.org/W6679434410","https://openalex.org/W6681017033","https://openalex.org/W6684191040","https://openalex.org/W6738460352","https://openalex.org/W6746200960","https://openalex.org/W6748269070","https://openalex.org/W6748636771","https://openalex.org/W6750531877","https://openalex.org/W6754054103","https://openalex.org/W6754416507","https://openalex.org/W6785482247"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776","https://openalex.org/W2041416246"],"abstract_inverted_index":{"This":[0,106],"paper":[1],"establishes":[2],"the":[3,17,28,44,52,56,71,81,111,115,139,144,152,156],"convergence":[4,57,127,157],"rates":[5],"for":[6,149],"fitting":[7],"a":[8,36,48,63,74,92,99,125,132],"polynomial":[9],"neural":[10],"network":[11],"with":[12,73],"quadratic":[13],"activation":[14],"function":[15,64],"via":[16],"mini-batch":[18,33,66,83,153],"Stochastic":[19,101],"Gradient":[20,102],"Descent":[21,103],"(SGD)":[22],"algorithm.":[23,105],"Specifically,":[24],"we":[25,69,119],"focus":[26],"on":[27,35],"parallel":[29],"implementation":[30],"of":[31,65,129,146,159],"calculating":[32],"gradients":[34],"distributed":[37,75],"computing":[38],"platform.":[39],"We":[40],"first":[41],"illustrate":[42],"that":[43,121],"SGD":[45,72,130],"converges":[46],"at":[47],"linear":[49],"rate":[50,58,128,158],"to":[51,89,91,131],"optimal":[53,134],"solution,":[54],"and":[55,87,151],"can":[59,108],"be":[60],"characterized":[61],"as":[62],"sizes.":[67],"Next,":[68],"deploy":[70],"approach":[76],"across":[77],"multiple":[78],"processors,":[79],"where":[80],"partial":[82],"gradient":[84],"is":[85],"calculated":[86],"quantized":[88],"send":[90],"master":[93],"processor":[94],"in":[95],"each":[96],"iteration,":[97],"yielding":[98],"Quantized":[100],"(QSGD)":[104],"scheme":[107],"effectively":[109],"reduce":[110],"communication":[112,140],"overhead":[113],"by":[114],"quantization":[116,150],"strategy.":[117],"Furthermore,":[118],"reveal":[120],"QSGD":[122],"provably":[123],"maintains":[124],"similar":[126],"globally":[133],"solution":[135],"while":[136],"significantly":[137],"reduces":[138],"cost.":[141],"In":[142],"particular,":[143],"number":[145],"bits":[147],"required":[148],"size":[154],"affect":[155],"QSGD.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}