{"id":"https://openalex.org/W4221072815","doi":"https://doi.org/10.1137/20m1376753","title":"QNG: A Quasi-Natural Gradient Method for Large-Scale Statistical Learning","display_name":"QNG: A Quasi-Natural Gradient Method for Large-Scale Statistical Learning","publication_year":2022,"publication_date":"2022-03-01","ids":{"openalex":"https://openalex.org/W4221072815","doi":"https://doi.org/10.1137/20m1376753"},"language":"en","primary_location":{"id":"doi:10.1137/20m1376753","is_oa":false,"landing_page_url":"https://doi.org/10.1137/20m1376753","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":"article","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/A5083554243","display_name":"Xiaoyu He","orcid":"https://orcid.org/0000-0003-4460-2460"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaoyu He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012731436","display_name":"Zibin Zheng","orcid":"https://orcid.org/0000-0001-7872-7718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zibin Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056123187","display_name":"Yuren Zhou","orcid":"https://orcid.org/0000-0002-0497-0835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuren Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100429133","display_name":"Chuan Chen","orcid":"https://orcid.org/0000-0002-7048-3445"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan Chen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083554243"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02721554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"1","first_page":"228","last_page":"255"},"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":0.9998000264167786,"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/T12676","display_name":"Machine Learning and ELM","score":0.9987999796867371,"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/broyden\u2013fletcher\u2013goldfarb\u2013shanno-algorithm","display_name":"Broyden\u2013Fletcher\u2013Goldfarb\u2013Shanno algorithm","score":0.6690413951873779},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6370757818222046},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6223593354225159},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.6122163534164429},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6018655300140381},{"id":"https://openalex.org/keywords/fisher-information","display_name":"Fisher information","score":0.5657570958137512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5617008805274963},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46711501479148865},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4415968060493469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4203642010688782},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40607649087905884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27995288372039795},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18018314242362976}],"concepts":[{"id":"https://openalex.org/C132721684","wikidata":"https://www.wikidata.org/wiki/Q2877013","display_name":"Broyden\u2013Fletcher\u2013Goldfarb\u2013Shanno algorithm","level":3,"score":0.6690413951873779},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6370757818222046},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6223593354225159},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.6122163534164429},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6018655300140381},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.5657570958137512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5617008805274963},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46711501479148865},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4415968060493469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4203642010688782},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40607649087905884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27995288372039795},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18018314242362976},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/20m1376753","is_oa":false,"landing_page_url":"https://doi.org/10.1137/20m1376753","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1599060605","display_name":null,"funder_award_id":"62006252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3668442405","display_name":null,"funder_award_id":"2021A1515011840","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G791997131","display_name":null,"funder_award_id":"2019A1515111154","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1970789124","https://openalex.org/W1994616650","https://openalex.org/W2020107577","https://openalex.org/W2051434435","https://openalex.org/W2051669046","https://openalex.org/W2073675454","https://openalex.org/W2096840748","https://openalex.org/W2133218851","https://openalex.org/W2149454052","https://openalex.org/W2166347285","https://openalex.org/W2805775373","https://openalex.org/W2895871047","https://openalex.org/W2962757795","https://openalex.org/W2963433607","https://openalex.org/W2963941964","https://openalex.org/W2964303576","https://openalex.org/W2990346675"],"related_works":["https://openalex.org/W2964045956","https://openalex.org/W2675954008","https://openalex.org/W1993561387","https://openalex.org/W4221162014","https://openalex.org/W3199158697","https://openalex.org/W2467023352","https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W1983625179"],"abstract_inverted_index":{"Natural":[0],"gradient":[1,45,152],"method":[2,46,95,111],"provides":[3],"a":[4,43,54],"powerful":[5],"paradigm":[6],"for":[7],"training":[8],"statistical":[9,65],"models":[10],"and":[11,28,67,122,143,154],"offers":[12],"several":[13,133],"appealing":[14],"theoretic":[15],"benefits.":[16],"It":[17,52],"constructs":[18],"the":[19,25,30,37,59,63,71,81,87,92,100,113,138,144,155],"Fisher":[20,72],"information":[21,61],"matrix":[22],"to":[23,47,57,68,79,150],"correct":[24],"ordinary":[26],"gradients,":[27],"thus,":[29],"cost":[31],"may":[32],"become":[33],"prohibitively":[34],"expensive":[35],"in":[36,91,126,140,146],"large-scale":[38],"setting.":[39],"This":[40,84],"paper":[41],"proposes":[42],"quasi-natural":[44],"address":[48],"this":[49],"computational":[50],"issue.":[51],"employs":[53],"rank-one":[55],"model":[56],"capture":[58],"second-order":[60],"from":[62],"underlying":[64],"manifold":[66],"iteratively":[69],"update":[70],"approximations.":[73],"A":[74],"three-loop":[75],"procedure":[76,85,90],"is":[77],"designed":[78],"implement":[80],"updating":[82],"formulas.":[83],"resembles":[86],"classical":[88],"two-loop":[89],"limited-memory":[93,157],"BFGS":[94,158],"but":[96],"saves":[97],"half":[98],"of":[99,117],"memory":[101],"usage":[102],"while":[103],"it":[104],"can":[105],"be":[106],"made":[107],"faster.":[108],"The":[109],"resulting":[110],"retains":[112],"convergence":[114,141],"rate":[115],"advantages":[116],"existing":[118],"stochastic":[119,151],"optimization":[120],"methods":[121],"has":[123],"inherent":[124],"ability":[125],"handling":[127],"nonconvexity.":[128],"Numerical":[129],"studies":[130],"conducted":[131],"on":[132],"machine":[134],"learning":[135],"tasks":[136],"demonstrate":[137],"reduction":[139],"time":[142],"robustness":[145],"tackling":[147],"nonconvexity":[148],"relative":[149],"descent":[153],"online":[156],"method.":[159]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}