{"id":"https://openalex.org/W3198924441","doi":"https://doi.org/10.1109/tpami.2021.3112139","title":"Improved Variance Reduction Methods for Riemannian Non-Convex Optimization","display_name":"Improved Variance Reduction Methods for Riemannian Non-Convex Optimization","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3198924441","doi":"https://doi.org/10.1109/tpami.2021.3112139","mag":"3198924441","pmid":"https://pubmed.ncbi.nlm.nih.gov/34516373"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3112139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3112139","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5031625303","display_name":"Andi Han","orcid":"https://orcid.org/0000-0003-4655-655X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Andi Han","raw_affiliation_strings":["Discipline of Business Analytics, University of Sydney Business School, University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Discipline of Business Analytics, University of Sydney Business School, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015817857","display_name":"Junbin Gao","orcid":"https://orcid.org/0000-0001-9803-0256"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junbin Gao","raw_affiliation_strings":["Discipline of Business Analytics, University of Sydney Business School, University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Discipline of Business Analytics, University of Sydney Business School, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031625303"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.2596,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83934903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"44","issue":"11","first_page":"7610","last_page":"7623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9983000159263611,"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/T10057","display_name":"Face and Expression Recognition","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/variance-reduction","display_name":"Variance reduction","score":0.6397004127502441},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6369606256484985},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5572851300239563},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5268579721450806},{"id":"https://openalex.org/keywords/riemannian-manifold","display_name":"Riemannian manifold","score":0.5115721821784973},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49263936281204224},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4735742509365082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4695625603199005},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.4279711842536926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42525556683540344},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.4193957448005676},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.41220730543136597},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3765481412410736},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.3382658362388611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27014636993408203},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.20341315865516663},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.16615760326385498},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10317283868789673},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1028396487236023}],"concepts":[{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.6397004127502441},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6369606256484985},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5572851300239563},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5268579721450806},{"id":"https://openalex.org/C2779593128","wikidata":"https://www.wikidata.org/wiki/Q632814","display_name":"Riemannian manifold","level":2,"score":0.5115721821784973},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49263936281204224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4735742509365082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4695625603199005},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.4279711842536926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42525556683540344},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.4193957448005676},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.41220730543136597},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3765481412410736},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3382658362388611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27014636993408203},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.20341315865516663},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.16615760326385498},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10317283868789673},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1028396487236023},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3112139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3112139","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34516373","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34516373","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8256825450","display_name":null,"funder_award_id":"DP200103015","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":108,"referenced_works":["https://openalex.org/W150914396","https://openalex.org/W1556236121","https://openalex.org/W1628278711","https://openalex.org/W1706213869","https://openalex.org/W1751687266","https://openalex.org/W1778935443","https://openalex.org/W1974766144","https://openalex.org/W1983496390","https://openalex.org/W2079354271","https://openalex.org/W2086161653","https://openalex.org/W2112796928","https://openalex.org/W2129812935","https://openalex.org/W2132968152","https://openalex.org/W2133323250","https://openalex.org/W2133848164","https://openalex.org/W2138674039","https://openalex.org/W2153635508","https://openalex.org/W2167623372","https://openalex.org/W2219888463","https://openalex.org/W2402588523","https://openalex.org/W2462905479","https://openalex.org/W2519358129","https://openalex.org/W2619167391","https://openalex.org/W2622263826","https://openalex.org/W2627006445","https://openalex.org/W2766164908","https://openalex.org/W2788611447","https://openalex.org/W2798738034","https://openalex.org/W2807088554","https://openalex.org/W2808953177","https://openalex.org/W2894101493","https://openalex.org/W2900348917","https://openalex.org/W2912255742","https://openalex.org/W2914057340","https://openalex.org/W2918466682","https://openalex.org/W2947854252","https://openalex.org/W2948034225","https://openalex.org/W2949228471","https://openalex.org/W2951689921","https://openalex.org/W2962867868","https://openalex.org/W2962890301","https://openalex.org/W2963248893","https://openalex.org/W2963959597","https://openalex.org/W2964303576","https://openalex.org/W2968543285","https://openalex.org/W2980089561","https://openalex.org/W2981869512","https://openalex.org/W2993258424","https://openalex.org/W3005728424","https://openalex.org/W3005767839","https://openalex.org/W3014908135","https://openalex.org/W3023902066","https://openalex.org/W3092448632","https://openalex.org/W3102317997","https://openalex.org/W3103296069","https://openalex.org/W3103657382","https://openalex.org/W3171665446","https://openalex.org/W4205293427","https://openalex.org/W4246883249","https://openalex.org/W4287901451","https://openalex.org/W4297785678","https://openalex.org/W4387168065","https://openalex.org/W6606191868","https://openalex.org/W6633160235","https://openalex.org/W6638045919","https://openalex.org/W6640590530","https://openalex.org/W6680196509","https://openalex.org/W6681668096","https://openalex.org/W6684641359","https://openalex.org/W6694978291","https://openalex.org/W6698038680","https://openalex.org/W6703949738","https://openalex.org/W6726332307","https://openalex.org/W6726983090","https://openalex.org/W6728561528","https://openalex.org/W6729295261","https://openalex.org/W6730130278","https://openalex.org/W6732127223","https://openalex.org/W6735387361","https://openalex.org/W6738699237","https://openalex.org/W6738954612","https://openalex.org/W6739622702","https://openalex.org/W6740708716","https://openalex.org/W6745410505","https://openalex.org/W6748326719","https://openalex.org/W6748386961","https://openalex.org/W6751777967","https://openalex.org/W6752223034","https://openalex.org/W6752458581","https://openalex.org/W6753122105","https://openalex.org/W6753849378","https://openalex.org/W6754432982","https://openalex.org/W6755578411","https://openalex.org/W6756082077","https://openalex.org/W6759119893","https://openalex.org/W6759796590","https://openalex.org/W6762577472","https://openalex.org/W6763175492","https://openalex.org/W6763586092","https://openalex.org/W6764252197","https://openalex.org/W6767560732","https://openalex.org/W6769109911","https://openalex.org/W6769589493","https://openalex.org/W6773347617","https://openalex.org/W6777210966","https://openalex.org/W6781810711","https://openalex.org/W6784098365","https://openalex.org/W6791051577"],"related_works":["https://openalex.org/W2107438106","https://openalex.org/W4283750944","https://openalex.org/W2193091921","https://openalex.org/W2774769449","https://openalex.org/W2303021954","https://openalex.org/W2205410708","https://openalex.org/W2901060063","https://openalex.org/W2526381590","https://openalex.org/W2951225533","https://openalex.org/W3127825571"],"abstract_inverted_index":{"Variance":[0],"reduction":[1,30,74],"is":[2,51,109],"popular":[3],"in":[4,112,189],"accelerating":[5],"gradient":[6,10,78,85],"descent":[7,11],"and":[8,20,38,61,64,84,91,106,159,173,187],"stochastic":[9,66],"for":[12,32,45,80,135,157,170],"optimization":[13,93],"problems":[14],"defined":[15],"on":[16,27,179],"both":[17,81,89],"euclidean":[18],"space":[19],"Riemannian":[21,34,175],"manifold.":[22],"This":[23],"paper":[24],"further":[25],"improves":[26],"existing":[28,56],"variance":[29,73],"methods":[31,75],"non-convex":[33,83],"optimization,":[35],"including":[36],"R-SVRG":[37,105,119,158],"R-SRG/R-SPIDER":[39],"by":[40,58],"providing":[41],"a":[42,180],"unified":[43],"framework":[44,50],"batch":[46,168],"size":[47,169],"adaptation.":[48],"Such":[49],"more":[52],"general":[53,82],"than":[54],"the":[55,71,97,102,113,142,146,152,164,185,190],"works":[57],"considering":[59],"retraction":[60],"vector":[62],"transport":[63],"mini-batch":[65],"gradients.":[67],"We":[68,115,130],"show":[69,132],"that":[70],"adaptive-batch":[72],"require":[76],"lower":[77],"complexities":[79,144],"dominated":[86],"functions,":[87],"under":[88,96,137],"finite-sum":[90],"online":[92,154],"settings.":[94],"Moreover,":[95],"new":[98],"framework,":[99],"we":[100,150,162],"complete":[101],"analysis":[103,186],"of":[104,118,166,182],"R-SRG,":[107],"which":[108,124,140],"currently":[110],"missing":[111],"literature.":[114],"prove":[116,151],"convergence":[117],"with":[120],"much":[121],"simpler":[122],"analysis,":[123],"leads":[125],"to":[126],"curvature-free":[127],"complexity":[128,155],"bounds.":[129],"also":[131],"improved":[133],"results":[134,156],"R-SRG":[136],"double-loop":[138],"convergence,":[139],"match":[141],"optimal":[143],"as":[145],"R-SPIDER.":[147],"In":[148],"addition,":[149],"first":[153],"R-SRG.":[160],"Lastly,":[161],"discuss":[163],"potential":[165],"adapting":[167],"non-smooth,":[171],"constrained":[172],"second-order":[174],"optimizers.":[176],"Extensive":[177],"experiments":[178],"variety":[181],"applications":[183],"support":[184],"claims":[188],"paper.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}