{"id":"https://openalex.org/W3204425029","doi":"https://doi.org/10.1145/3458744.3474050","title":"Accelerating Neural Network Training using Arbitrary Precision Approximating Matrix Multiplication Algorithms","display_name":"Accelerating Neural Network Training using Arbitrary Precision Approximating Matrix Multiplication Algorithms","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3204425029","doi":"https://doi.org/10.1145/3458744.3474050","mag":"3204425029"},"language":"en","primary_location":{"id":"doi:10.1145/3458744.3474050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458744.3474050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing Workshop","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/A5064243391","display_name":"Grey Ballard","orcid":"https://orcid.org/0000-0003-1557-8027"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grey Ballard","raw_affiliation_strings":["Wake Forest University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University, United States of America","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002717530","display_name":"Jack Weissenberger","orcid":null},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Weissenberger","raw_affiliation_strings":["Wake Forest University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University, United States of America","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010924875","display_name":"Luoping Zhang","orcid":"https://orcid.org/0000-0002-0112-1141"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luoping Zhang","raw_affiliation_strings":["Wake Forest University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University, United States of America","institution_ids":["https://openalex.org/I47251452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47251452"],"apc_list":null,"apc_paid":null,"fwci":0.2864,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61052026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9955000281333923,"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":0.9955000281333923,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.993399977684021,"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/matrix-multiplication","display_name":"Matrix multiplication","score":0.7712541818618774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.754798173904419},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.7509175539016724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6841828227043152},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.640703022480011},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5975975394248962},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5719218850135803},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5460671186447144},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5457030534744263},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4708157181739807},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.42413991689682007},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33234575390815735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22165557742118835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1502474844455719}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7712541818618774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754798173904419},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.7509175539016724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6841828227043152},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.640703022480011},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5975975394248962},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5719218850135803},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5460671186447144},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5457030534744263},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4708157181739807},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.42413991689682007},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33234575390815735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22165557742118835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1502474844455719},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458744.3474050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458744.3474050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4332098366","display_name":"CAREER: Communication-Avoiding Tensor Decomposition Algorithms","funder_award_id":"1942892","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W651903736","https://openalex.org/W1707645771","https://openalex.org/W1964758312","https://openalex.org/W1967534352","https://openalex.org/W1996440503","https://openalex.org/W2002048434","https://openalex.org/W2004948173","https://openalex.org/W2019603005","https://openalex.org/W2023489834","https://openalex.org/W2023724794","https://openalex.org/W2028087580","https://openalex.org/W2035476608","https://openalex.org/W2038073775","https://openalex.org/W2080063509","https://openalex.org/W2112796928","https://openalex.org/W2137983211","https://openalex.org/W2493665548","https://openalex.org/W2546792675","https://openalex.org/W3001665736","https://openalex.org/W3014127403","https://openalex.org/W3021804876","https://openalex.org/W3116253690","https://openalex.org/W4244832872","https://openalex.org/W4247950230","https://openalex.org/W4253696084"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Matrix":[0],"multiplication":[1,30],"is":[2],"one":[3,119],"of":[4,114,161,181],"the":[5,10,19,46,111,115,141,177,182],"bottleneck":[6],"computations":[7],"for":[8,28,81,99],"training":[9,20,142,176],"weights":[11],"within":[12],"deep":[13],"neural":[14,85],"networks.":[15],"To":[16],"speed":[17],"up":[18,104,162,171],"phase,":[21],"we":[22],"propose":[23],"to":[24,102,105,129,163,172],"use":[25],"faster":[26],"algorithms":[27,39,69,92,128],"matrix":[29],"known":[31],"as":[32],"Arbitrary":[33],"Precision":[34],"Approximating":[35],"(APA)":[36],"algorithms.":[37],"APA":[38,68,91],"perform":[40],"asymptotically":[41],"fewer":[42],"arithmetic":[43],"operations":[44],"than":[45],"classical":[47,116],"algorithm,":[48],"but":[49],"they":[50],"compute":[51],"an":[52,56],"approximate":[53],"result":[54],"with":[55],"error":[57],"that":[58,90],"can":[59,93],"be":[60,94],"made":[61],"arbitrarily":[62],"small":[63],"in":[64,73,140],"exact":[65],"arithmetic.":[66],"Practical":[67],"provide":[70,78],"significant":[71,138],"reduction":[72,139],"computation":[74],"time":[75],"and":[76,97,107,121,157,165],"still":[77],"enough":[79],"accuracy":[80],"many":[82],"applications":[83],"like":[84],"network":[86,135,153],"training.":[87],"We":[88,168],"demonstrate":[89,170],"efficiently":[95],"implemented":[96],"parallelized":[98],"multicore":[100],"CPUs":[101],"obtain":[103],"28%":[106],"21%":[108],"speedups":[109],"over":[110],"fastest":[112],"implementation":[113],"algorithm":[117],"using":[118,126],"core":[120],"12":[122],"cores,":[123],"respectively.":[124,167],"Furthermore,":[125],"these":[127],"train":[130],"a":[131,150],"Multi-Layer":[132],"Perceptron":[133],"(MLP)":[134],"yields":[136],"no":[137],"or":[143],"testing":[144],"error.":[145],"Our":[146],"performance":[147,159],"results":[148],"on":[149],"large":[151],"MLP":[152],"show":[154],"overall":[155],"sequential":[156],"multithreaded":[158],"improvements":[160],"25%":[164],"13%,":[166],"also":[169],"15%":[173],"improvement":[174],"when":[175],"fully":[178],"connected":[179],"layers":[180],"VGG-19":[183],"image":[184],"classification":[185],"network.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}