{"id":"https://openalex.org/W2912745458","doi":"https://doi.org/10.1137/19m130858x","title":"Dual Space Preconditioning for Gradient Descent","display_name":"Dual Space Preconditioning for Gradient Descent","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W2912745458","doi":"https://doi.org/10.1137/19m130858x","mag":"2912745458"},"language":"en","primary_location":{"id":"doi:10.1137/19m130858x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/19m130858x","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.02257","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054711904","display_name":"Chris J. Maddison","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chris J. Maddison","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041259048","display_name":"Daniel Paulin","orcid":"https://orcid.org/0000-0001-7837-6452"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Paulin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103835353","display_name":"Yee Whye Teh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yee Whye Teh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091677854","display_name":"Randal Douc","orcid":"https://orcid.org/0000-0003-3910-9495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnaud Doucet","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054711904"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.00305056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":"1","first_page":"991","last_page":"1016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9948999881744385,"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"}},{"id":"https://openalex.org/T12209","display_name":"Bone and Joint Diseases","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2732","display_name":"Orthopedics and Sports Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.7212907671928406},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.7060926556587219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.7053747177124023},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.6530430912971497},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6078423261642456},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5846121311187744},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5467383861541748},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.5438410043716431},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.5023949146270752},{"id":"https://openalex.org/keywords/nonlinear-conjugate-gradient-method","display_name":"Nonlinear conjugate gradient method","score":0.46536827087402344},{"id":"https://openalex.org/keywords/bregman-divergence","display_name":"Bregman divergence","score":0.45077773928642273},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.42350298166275024},{"id":"https://openalex.org/keywords/proximal-gradient-methods","display_name":"Proximal Gradient Methods","score":0.4101405739784241},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.40531817078590393},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37498044967651367},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.3422582149505615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.15004631876945496},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10201558470726013}],"concepts":[{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.7212907671928406},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.7060926556587219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7053747177124023},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6530430912971497},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6078423261642456},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5846121311187744},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5467383861541748},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.5438410043716431},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.5023949146270752},{"id":"https://openalex.org/C26362088","wikidata":"https://www.wikidata.org/wiki/Q17086453","display_name":"Nonlinear conjugate gradient method","level":4,"score":0.46536827087402344},{"id":"https://openalex.org/C149073432","wikidata":"https://www.wikidata.org/wiki/Q4960382","display_name":"Bregman divergence","level":2,"score":0.45077773928642273},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.42350298166275024},{"id":"https://openalex.org/C10494615","wikidata":"https://www.wikidata.org/wiki/Q17086765","display_name":"Proximal Gradient Methods","level":4,"score":0.4101405739784241},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.40531817078590393},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37498044967651367},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3422582149505615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.15004631876945496},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10201558470726013},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1137/19m130858x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/19m130858x","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1902.02257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.02257","pdf_url":"https://arxiv.org/pdf/1902.02257","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:pure.ed.ac.uk:publications/080e540d-288d-4830-b7e9-0331b5a3dfc9","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/080e540d-288d-4830-b7e9-0331b5a3dfc9","pdf_url":"http://hdl.handle.net/20.500.11820/080e540d-288d-4830-b7e9-0331b5a3dfc9","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Maddison, C, Paulin, D, Doucet, A & The, Y W 2021, 'Dual Space Preconditioning for Gradient Descent', Siam journal on optimization, vol. 31, no. 1, pp. 991-1016. https://doi.org/10.1137/19M130858X","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:2912745458","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1902.02257.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.1902.02257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.02257","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.02257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.02257","pdf_url":"https://arxiv.org/pdf/1902.02257","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G1348705749","display_name":null,"funder_award_id":"617071","funder_id":"https://openalex.org/F4320333065","funder_display_name":"Seventh Framework Programme"},{"id":"https://openalex.org/G1871434800","display_name":null,"funder_award_id":"EP/R034710/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3402893575","display_name":null,"funder_award_id":"EP/R018561/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4037990431","display_name":"Semantic Information Pursuit for Multimodal Data Analysis","funder_award_id":"EP/R013616/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6062536210","display_name":null,"funder_award_id":"PGSD3-460176-2014","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6194403621","display_name":null,"funder_award_id":"EP/R013616/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320311643","display_name":"Ministry of Defence","ror":"https://ror.org/01bvxzn29"},{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320333065","display_name":"Seventh Framework Programme","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334649","display_name":"Institute for Advanced Studies in the Humanities, University of Edinburgh","ror":"https://ror.org/01nrxwf90"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W231615869","https://openalex.org/W568673721","https://openalex.org/W1428340059","https://openalex.org/W1506342804","https://openalex.org/W1509803206","https://openalex.org/W1560263223","https://openalex.org/W1568288633","https://openalex.org/W1966394100","https://openalex.org/W1970986119","https://openalex.org/W1980404857","https://openalex.org/W1981041832","https://openalex.org/W1981220107","https://openalex.org/W1982143037","https://openalex.org/W2011243226","https://openalex.org/W2016384870","https://openalex.org/W2033468335","https://openalex.org/W2050310885","https://openalex.org/W2085401202","https://openalex.org/W2088624648","https://openalex.org/W2096765209","https://openalex.org/W2105277645","https://openalex.org/W2114605231","https://openalex.org/W2118075434","https://openalex.org/W2130756427","https://openalex.org/W2135125546","https://openalex.org/W2150865801","https://openalex.org/W2296319761","https://openalex.org/W2316564661","https://openalex.org/W2535496140","https://openalex.org/W2551153860","https://openalex.org/W2793948820","https://openalex.org/W2800693632","https://openalex.org/W2808862920","https://openalex.org/W2885777113","https://openalex.org/W2889795689","https://openalex.org/W2905950575","https://openalex.org/W2915226774","https://openalex.org/W2962706047","https://openalex.org/W2963182236","https://openalex.org/W2963189955","https://openalex.org/W2963248893","https://openalex.org/W2963353224","https://openalex.org/W2963388608","https://openalex.org/W2963681631","https://openalex.org/W2963967579","https://openalex.org/W2964347994","https://openalex.org/W2970344166","https://openalex.org/W2972333651","https://openalex.org/W3002376889","https://openalex.org/W3136201867","https://openalex.org/W4211094263"],"related_works":["https://openalex.org/W2947416323","https://openalex.org/W3162537520","https://openalex.org/W2949979820","https://openalex.org/W2970466834","https://openalex.org/W2963248893","https://openalex.org/W2796161934","https://openalex.org/W2512490502","https://openalex.org/W2586039889","https://openalex.org/W3003113518","https://openalex.org/W2514742857","https://openalex.org/W1159291337","https://openalex.org/W2594900731","https://openalex.org/W2969687526","https://openalex.org/W2187022721","https://openalex.org/W2913096093","https://openalex.org/W3177586498","https://openalex.org/W3183530383","https://openalex.org/W2390078254","https://openalex.org/W2956019824","https://openalex.org/W2108763700"],"abstract_inverted_index":{"The":[0],"conditions":[1],"of":[2,15,49,69,113,117],"relative":[3,6,50,57,82],"smoothness":[4,51,58],"and":[5,31,65,72,137],"strong":[7,83],"convexity":[8],"were":[9],"recently":[10],"introduced":[11],"for":[12,19,28],"the":[13,53,62,66,70,75,115],"analysis":[14],"Bregman":[16,103],"gradient":[17,29,78,104,118,125],"methods":[18],"convex":[20,40,67,128],"optimization.":[21],"We":[22,130],"introduce":[23],"a":[24,90,123],"generalized":[25,91],"left-preconditioning":[26],"method":[27,110,133],"descent":[30,119],"show":[32],"that":[33,94],"its":[34],"convergence":[35,88],"on":[36,120,134],"an":[37,47],"essentially":[38],"smooth":[39],"objective":[41],"function":[42,140],"can":[43],"be":[44],"guaranteed":[45],"via":[46],"application":[48],"in":[52,107],"dual":[54,81],"space.":[55],"Our":[56],"assumption":[59],"is":[60,95,111],"between":[61],"designed":[63],"preconditioner":[64],"conjugate":[68],"objective,":[71],"it":[73,101],"generalizes":[74],"typical":[76],"Lipschitz":[77],"assumption.":[79],"Under":[80],"convexity,":[84],"we":[85],"obtain":[86],"linear":[87],"with":[89,122],"condition":[92],"number":[93],"invariant":[96],"under":[97],"horizontal":[98],"translations,":[99],"distinguishing":[100],"from":[102],"methods.":[105],"Thus,":[106],"principle":[108],"our":[109,132],"capable":[112],"improving":[114],"conditioning":[116],"problems":[121],"non-Lipschitz":[124],"or":[126],"nonstrongly":[127],"structure.":[129],"demonstrate":[131],"$p$-norm":[135],"regression":[136],"exponential":[138],"penalty":[139],"minimization.":[141]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}