{"id":"https://openalex.org/W2791562219","doi":"https://doi.org/10.23919/eusipco.2018.8553369","title":"Fast Convergence for Stochastic and Distributed Gradient Descent in the Interpolation Limit","display_name":"Fast Convergence for Stochastic and Distributed Gradient Descent in the Interpolation Limit","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2791562219","doi":"https://doi.org/10.23919/eusipco.2018.8553369","mag":"2791562219"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2018.8553369","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.02922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037732748","display_name":"Partha P. Mitra","orcid":"https://orcid.org/0000-0001-8818-6804"},"institutions":[{"id":"https://openalex.org/I2750212522","display_name":"Cold Spring Harbor Laboratory","ror":"https://ror.org/02qz8b764","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2750212522"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Partha P Mitra","raw_affiliation_strings":["Cold Spring, Cold Spring Harbor Laboratory, Harbor, USA","Cold Spring, Cold Spring Harbor Laboratory, Harbor, NY11724, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cold Spring, Cold Spring Harbor Laboratory, Harbor, USA","institution_ids":["https://openalex.org/I2750212522"]},{"raw_affiliation_string":"Cold Spring, Cold Spring Harbor Laboratory, Harbor, NY11724, USA","institution_ids":["https://openalex.org/I2750212522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5037732748"],"corresponding_institution_ids":["https://openalex.org/I2750212522"],"apc_list":null,"apc_paid":null,"fwci":0.1132,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35035123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1890","last_page":"1894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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":1.0,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9948999881744385,"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/mathematics","display_name":"Mathematics","score":0.6550591588020325},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5874881148338318},{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.5358675122261047},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5127424001693726},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.5050466656684875},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5041481256484985},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.46005767583847046},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.4475822150707245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44697698950767517},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4437946379184723},{"id":"https://openalex.org/keywords/lambda","display_name":"Lambda","score":0.4383554756641388},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41954296827316284},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.40911638736724854},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.35644209384918213},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3440425992012024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2209126055240631},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.191156268119812},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15470942854881287}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6550591588020325},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5874881148338318},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.5358675122261047},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5127424001693726},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5050466656684875},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5041481256484985},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.46005767583847046},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.4475822150707245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44697698950767517},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4437946379184723},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.4383554756641388},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41954296827316284},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.40911638736724854},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.35644209384918213},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3440425992012024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2209126055240631},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.191156268119812},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15470942854881287},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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":6,"locations":[{"id":"doi:10.23919/eusipco.2018.8553369","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cshl.edu:41254","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402288","display_name":"Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Paper"},{"id":"pmh:oai:arXiv.org:1803.02922","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.02922","pdf_url":"https://arxiv.org/pdf/1803.02922","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2791562219","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.02922","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:repository.cshl.edu:37665","is_oa":false,"landing_page_url":"http://repository.cshl.edu/37665/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402288","display_name":"Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book"},{"id":"doi:10.48550/arxiv.1803.02922","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.02922","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.02922","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.02922","pdf_url":"https://arxiv.org/pdf/1803.02922","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322211","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2791562219.pdf"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1496894444","https://openalex.org/W2048305372","https://openalex.org/W2164278908","https://openalex.org/W2622263826","https://openalex.org/W4292363360","https://openalex.org/W6684859321","https://openalex.org/W6740154879"],"related_works":["https://openalex.org/W3100482347","https://openalex.org/W2964271537","https://openalex.org/W3009274618","https://openalex.org/W3023160755","https://openalex.org/W2966363981","https://openalex.org/W2770027754","https://openalex.org/W2922277331","https://openalex.org/W1866529865","https://openalex.org/W3127328563","https://openalex.org/W2971899460","https://openalex.org/W3114838575","https://openalex.org/W3011567503","https://openalex.org/W3158434734","https://openalex.org/W2788216258","https://openalex.org/W1483514891","https://openalex.org/W2786829989","https://openalex.org/W2971032006","https://openalex.org/W3151731968","https://openalex.org/W2885194143","https://openalex.org/W2619445139"],"abstract_inverted_index":{"Modern":[0],"supervised":[1],"learning":[2,267],"techniques,":[3],"particularly":[4],"those":[5],"using":[6],"deep":[7],"nets,":[8],"involve":[9],"fitting":[10],"high":[11],"dimensional":[12],"labelled":[13],"data":[14],"sets":[15],"with":[16,197,200,219],"functions":[17,45,225],"containing":[18],"very":[19],"large":[20],"numbers":[21],"of":[22,25,42,57,65,104,173,209,222,256,264],"parameters.":[23],"Much":[24],"this":[26,111,187],"work":[27],"is":[28,87,184,204,236],"empirical.":[29],"Interesting":[30],"phenomena":[31],"have":[32],"been":[33,52],"observed":[34],"that":[35,54,186],"require":[36],"theoretical":[37,262],"explanations;":[38],"however":[39],"the":[40,43,47,55,63,66,73,91,101,105,126,135,178,193,205,210,214,232,241,254,257,261],"non-convexity":[41],"loss":[44,106,147],"complicates":[46],"analysis.":[48],"Recently":[49],"it":[50,235],"has":[51],"proposed":[53],"success":[56],"these":[58],"techniques":[59],"rests":[60],"partly":[61],"in":[62,72,78,125,134,231,260],"effectiveness":[64],"simple":[67,144],"stochastic":[68,97],"gradient":[69,122,139],"descent":[70,140],"algorithm":[71,93,120,132,189],"so":[74],"called":[75],"interpolation":[76,258],"limit":[77,234,259],"which":[79],"all":[80],"labels":[81],"are":[82],"fit":[83],"perfectly.":[84],"This":[85],"analysis":[86,251],"made":[88],"possible":[89],"since":[90],"SGD":[92,131],"reduces":[94,195],"to":[95,138,142,226,239,244,248],"a":[96,117,143,174,201],"linear":[98],"system":[99],"near":[100],"interpolating":[102,127,233],"minimum":[103],"function.":[107],"Here":[108,158],"we":[109],"exploit":[110],"insight":[112],"by":[113],"presenting":[114],"and":[115,165],"analyzing":[116],"new":[118],"distributed":[119,130,146,188],"for":[121,246],"descent,":[123],"also":[124],"limit.":[128],"The":[129,170,250],"presented":[133],"paper":[136],"corresponds":[137],"applied":[141],"penalized":[145],"function,":[148],"L(w1,":[149],"...,":[150],"wn)":[151],"=":[152],"\u03a3ili(wi)":[153],"+":[154],"\u03bc":[155],"\u03a3<;i,j><;/i,j>|wi-":[156],"wj|2.":[157],"each":[159],"node":[160],"holds":[161],"only":[162],"one":[163],"sample,":[164],"its":[166],"own":[167],"parameter":[168,243],"vector.":[169],"notationdenotes":[171],"edges":[172],"connected":[175],"graph":[176],"defining":[177],"communication":[179],"links":[180],"between":[181,229],"nodes.":[182],"It":[183],"shown":[185],"converges":[190],"linearly":[191],"(ie":[192],"error":[194],"exponentially":[196],"iteration":[198],"number),":[199],"rate":[202],"1-\u03b7/n\u03bbmin(H)min(H)":[203],"smallest":[206],"nonzero":[207],"eigenvalue":[208],"sample":[211],"covariance":[212],"or":[213],"Hessian":[215],"H.":[216],"In":[217],"contrast":[218],"previous":[220],"usage":[221],"similar":[223],"penalty":[224,242],"enforce":[227],"consensus":[228,247],"nodes,":[230],"not":[237],"required":[238],"take":[240],"infinity":[245],"occur.":[249],"further":[252],"reinforces":[253],"utility":[255],"treatment":[263],"modern":[265],"machine":[266],"algorithms.":[268]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}