{"id":"https://openalex.org/W2791715162","doi":"https://doi.org/10.1145/3219819.3220075","title":"A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization","display_name":"A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2791715162","doi":"https://doi.org/10.1145/3219819.3220075","mag":"2791715162"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3220075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3220075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220075","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220075","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ching-pei Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-pei Lee","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cong Han Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Han Lim","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":null,"display_name":"Stephen J. Wright","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen J. Wright","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":1.8252,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90083279,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1646","last_page":"1655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"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/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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.691100001335144},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.583899974822998},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5490999817848206},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5073000192642212},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4961000084877014},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49059998989105225},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4571000039577484},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4569000005722046}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.691100001335144},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.559499979019165},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5436999797821045},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4961000084877014},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47699999809265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4659000039100647},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.4041999876499176},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C122268817","wikidata":"https://www.wikidata.org/wiki/Q2020318","display_name":"Frank\u2013Wolfe algorithm","level":5,"score":0.34940001368522644},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C79248915","wikidata":"https://www.wikidata.org/wiki/Q17086776","display_name":"Proximal gradient methods for learning","level":5,"score":0.2935999929904938},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.265500009059906}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3219819.3220075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3220075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220075","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.01370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.01370","pdf_url":"https://arxiv.org/pdf/1803.01370","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"}],"best_oa_location":{"id":"doi:10.1145/3219819.3220075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3220075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3220075","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G123809044","display_name":null,"funder_award_id":"IIS-1447449, 1628384, 1634597, and 1740707","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2036146391","display_name":null,"funder_award_id":"Subcontract 3F-30222","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2791715162.pdf","grobid_xml":"https://content.openalex.org/works/W2791715162.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W343801824","https://openalex.org/W1983599491","https://openalex.org/W2030161963","https://openalex.org/W2039050532","https://openalex.org/W2064217481","https://openalex.org/W2065030431","https://openalex.org/W2089442574","https://openalex.org/W2114515438","https://openalex.org/W2126607811","https://openalex.org/W2936995161","https://openalex.org/W2962748029","https://openalex.org/W2963173886"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,17,66,77],"communication-":[3],"and":[4,23,50,61,130],"computation-efficient":[5],"distributed":[6,36,67],"optimization":[7],"algorithm":[8,45],"using":[9],"second-order":[10,22],"information":[11],"for":[12,26,41,76],"solving":[13],"ERM":[14],"problems":[15,83,120],"with":[16],"nonsmooth":[18],"regularization":[19],"term.":[20],"Current":[21],"quasi-Newton":[24],"methods":[25],"this":[27],"problem":[28],"either":[29],"do":[30],"not":[31],"work":[32,39],"well":[33],"in":[34,65],"the":[35,59,86,104,134],"setting":[37],"or":[38],"only":[40],"specific":[42],"regularizers.":[43],"Our":[44],"uses":[46],"successive":[47],"quadratic":[48],"approximations,":[49],"we":[51],"describe":[52],"how":[53],"to":[54,106],"maintain":[55],"an":[56],"approximation":[57],"of":[58,80],"Hessian":[60],"solve":[62],"subproblems":[63],"efficiently":[64],"manner.":[68],"The":[69],"proposed":[70],"method":[71,124],"enjoys":[72],"global":[73],"linear":[74],"convergence":[75],"broad":[78],"range":[79],"non-strongly":[81],"convex":[82,119],"that":[84,122],"includes":[85],"most":[87],"commonly":[88],"used":[89,108],"ERMs,":[90],"thus":[91],"requiring":[92],"lower":[93],"communication":[94,128],"complexity.":[95],"It":[96],"also":[97],"converges":[98],"on":[99,109,118,127],"non-convex":[100],"problems,":[101],"so":[102],"has":[103],"potential":[105],"be":[107],"applications":[110],"such":[111],"as":[112],"deep":[113],"learning.":[114],"Initial":[115],"computational":[116],"results":[117],"demonstrate":[121],"our":[123],"significantly":[125],"improves":[126],"cost":[129],"running":[131],"time":[132],"over":[133],"current":[135],"state-of-the-art":[136],"methods.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2018-03-29T00:00:00"}