{"id":"https://openalex.org/W2963540381","doi":null,"title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","display_name":"Gradient Sparsification for Communication-Efficient Distributed Optimization","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963540381","mag":"2963540381"},"language":"en","primary_location":{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-98061","doi":null,"is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-98061","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5050515088","display_name":"Jianqiao Wangni","orcid":"https://orcid.org/0000-0002-4454-1744","observed_orcids":["https://orcid.org/0000-0002-4454-1744"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianqiao Wangni","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, United States"],"raw_orcid":"https://orcid.org/0000-0002-4454-1744","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628036","display_name":"Jialei Wang","orcid":"https://orcid.org/0000-0001-7556-4941","observed_orcids":["https://orcid.org/0000-0001-7556-4941"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jialei Wang","raw_affiliation_strings":["University of Chicago, Chicago, United States"],"raw_orcid":"https://orcid.org/0000-0001-7556-4941","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, United States","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ji Liu","orcid":"https://orcid.org/0000-0002-5509-5065","observed_orcids":["https://orcid.org/0000-0002-5509-5065"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["University of Rochester, Rochester, United States"],"raw_orcid":"https://orcid.org/0000-0002-5509-5065","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, United States","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558","observed_orcids":["https://orcid.org/0000-0002-5511-2558","https://orcid.org/0000-0001-5818-4285","https://orcid.org/0000-0002-7025-6365","https://orcid.org/0000-0002-8838-4963","https://orcid.org/0000-0001-6212-4891","https://orcid.org/0000-0002-3506-0180","https://orcid.org/0000-0002-6807-0641","https://orcid.org/0000-0003-1148-4322","https://orcid.org/0000-0002-0131-0129","https://orcid.org/0000-0001-8163-3050","https://orcid.org/0000-0002-3481-6062"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Rutgers, The State University of New Jersey, New Brunswick, United States"],"raw_orcid":"https://orcid.org/0000-0002-5511-2558","affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey, New Brunswick, United States","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.0062,"has_fulltext":false,"cited_by_count":179,"citation_normalized_percentile":{"value":0.99062885,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"1299","last_page":"1309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":9.999999747378752e-05,"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/gradient-sparsification","display_name":"gradient sparsification","score":0.9580000042915344},{"id":"https://openalex.org/keywords/communication-efficiency","display_name":"communication efficiency","score":0.8500000238418579},{"id":"https://openalex.org/keywords/distributed-optimization","display_name":"distributed optimization","score":0.9950000047683716},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.7960000038146973},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"convex optimization","score":0.6140000224113464},{"id":"https://openalex.org/keywords/tikhonov-regularization","display_name":"Tikhonov regularization","score":0.5680000185966492},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.9240000247955322},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.9950000047683716},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009605765342712},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6502220034599304},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5555251836776733},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.4865218997001648},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48127835988998413},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46974995732307434},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4634295403957367},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4620167016983032},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.43693313002586365},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37485820055007935},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3688742518424988},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3003356456756592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24613234400749207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2109878659248352},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":3,"locations":[{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-98061","doi":null,"is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-98061","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-98061","doi":null,"is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85062695192&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"mag:2963540381","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/7405-gradient-sparsification-for-communication-efficient-distributed-optimization.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2948746540","https://openalex.org/W4399154140","https://openalex.org/W2890924858","https://openalex.org/W3114950976","https://openalex.org/W7165611878","https://openalex.org/W4210558419","https://openalex.org/W3164396303","https://openalex.org/W4320015028","https://openalex.org/W3090675293","https://openalex.org/W3087165870"],"abstract_inverted_index":{"Modern":[0],"large-scale":[1],"machine":[2],"learning":[3],"applications":[4],"require":[5],"stochastic":[6,28,53,66],"optimization":[7,45],"algorithms":[8],"to":[9,36,47,59,75,80],"be":[10,81],"implemented":[11],"on":[12,107],"distributed":[13],"computational":[14],"architectures.":[15],"A":[16],"key":[17,56],"bottleneck":[18],"is":[19,58,94],"the":[20,38,49,65,71,77,85],"communication":[21,39],"overhead":[22],"for":[23,96,104],"exchanging":[24],"information":[25],"such":[26],"as":[27],"gradients":[29],"among":[30],"different":[31],"workers.":[32],"In":[33],"this":[34],"paper,":[35],"reduce":[37],"cost,":[40],"we":[41],"propose":[42],"a":[43,89,101],"convex":[44],"formulation":[46],"minimize":[48],"coding":[50],"length":[51],"of":[52,64],"gradients.":[54],"The":[55],"idea":[57],"randomly":[60],"drop":[61],"out":[62],"coordinates":[63,73],"gradient":[67,79],"vectors":[68],"and":[69,91,114],"amplify":[70],"remaining":[72],"appropriately":[74],"ensure":[76],"sparsified":[78],"unbiased.":[82],"To":[83],"solve":[84],"optimal":[86],"sparsification":[87,120],"efficiently,":[88],"simple":[90],"fast":[92],"algorithm":[93],"proposed":[95],"an":[97],"approximate":[98],"solution,":[99],"with":[100],"theoretical":[102],"guarantee":[103],"sparseness.":[105],"Experiments":[106],"`2-regularized":[108],"logistic":[109],"regression,":[110],"support":[111],"vector":[112],"machines":[113],"convolutional":[115],"neural":[116],"networks":[117],"validate":[118],"our":[119],"approaches.":[121]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":74},{"year":2020,"cited_by_count":66},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":4}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2019-07-30T00:00:00"}