{"id":"https://openalex.org/W3094036653","doi":"https://doi.org/10.1109/dslw51110.2021.9523407","title":"Low-Rank Matrix Recovery with Scaled Subgradient Methods: Fast and Robust Convergence Without the Condition Number","display_name":"Low-Rank Matrix Recovery with Scaled Subgradient Methods: Fast and Robust Convergence Without the Condition Number","publication_year":2021,"publication_date":"2021-06-05","ids":{"openalex":"https://openalex.org/W3094036653","doi":"https://doi.org/10.1109/dslw51110.2021.9523407","mag":"3094036653"},"language":"en","primary_location":{"id":"doi:10.1109/dslw51110.2021.9523407","doi":"https://doi.org/10.1109/dslw51110.2021.9523407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dslw51110.2021.9523407","pdf_url":null,"source":{"id":"https://openalex.org/S7407096592","display_name":"IEEE Data Science Workshop (DSW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Data Science and Learning Workshop (DSLW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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":null,"display_name":"Tian Tong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Tong","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074490643","display_name":"Cong Ma","orcid":"https://orcid.org/0000-0003-2532-0038","observed_orcids":["https://orcid.org/0000-0003-2532-0038"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Ma","raw_affiliation_strings":["UC Berkeley, Berkeley, CA 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053809095","display_name":"Yuejie Chi","orcid":"https://orcid.org/0000-0002-6766-5459","observed_orcids":["https://orcid.org/0000-0002-6766-5459"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuejie Chi","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.103,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90109133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/low-rank-matrix-recovery","display_name":"low-rank matrix recovery","score":0.9990000128746033},{"id":"https://openalex.org/keywords/robust-convergence","display_name":"robust convergence","score":0.3930000066757202},{"id":"https://openalex.org/keywords/matrix-factorization","display_name":"matrix factorization","score":0.5389999747276306},{"id":"https://openalex.org/keywords/robust-pca","display_name":"robust principal component analysis","score":0.36800000071525574},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.6050000190734863},{"id":"https://openalex.org/keywords/nonsmooth-optimization","display_name":"nonsmooth optimization","score":0.8119999766349792}],"concepts":[{"id":"https://openalex.org/C158968445","wikidata":"https://www.wikidata.org/wiki/Q7631150","display_name":"Subgradient method","level":2,"score":0.6837068200111389},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6779887080192566},{"id":"https://openalex.org/C90199385","wikidata":"https://www.wikidata.org/wiki/Q6692777","display_name":"Low-rank approximation","level":3,"score":0.608412504196167},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5664862990379333},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5662598013877869},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5429044365882874},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5078635811805725},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4844515323638916},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4827922582626343},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4223668873310089},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.41346442699432373},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38869982957839966},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3805159330368042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.24571442604064941},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12116888165473938},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.09457802772521973},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0899178683757782},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dslw51110.2021.9523407","doi":"https://doi.org/10.1109/dslw51110.2021.9523407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dslw51110.2021.9523407","pdf_url":null,"source":{"id":"https://openalex.org/S7407096592","display_name":"IEEE Data Science Workshop (DSW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Data Science and Learning Workshop (DSLW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.8199999928474426,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1548998364","https://openalex.org/W1573301526","https://openalex.org/W1884015253","https://openalex.org/W2008164266","https://openalex.org/W2106005123","https://openalex.org/W2110451175","https://openalex.org/W2116837464","https://openalex.org/W2118550318","https://openalex.org/W2124252039","https://openalex.org/W2133105246","https://openalex.org/W2142949395","https://openalex.org/W2224829387","https://openalex.org/W2268674159","https://openalex.org/W2296832563","https://openalex.org/W2462226338","https://openalex.org/W2511406830","https://openalex.org/W2767603038","https://openalex.org/W2768927505","https://openalex.org/W2783859821","https://openalex.org/W2788506892","https://openalex.org/W2790687101","https://openalex.org/W2798818710","https://openalex.org/W2810541051","https://openalex.org/W2942284548","https://openalex.org/W2962909343","https://openalex.org/W2963099043","https://openalex.org/W2963537367","https://openalex.org/W2963685382","https://openalex.org/W2963945345","https://openalex.org/W2964317091","https://openalex.org/W2969215180","https://openalex.org/W2985894713","https://openalex.org/W2990899841","https://openalex.org/W3007343725","https://openalex.org/W3015130385","https://openalex.org/W3025612414","https://openalex.org/W3118581654"],"related_works":["https://openalex.org/W2942284548","https://openalex.org/W3199369086","https://openalex.org/W3007343725","https://openalex.org/W7148537597","https://openalex.org/W6921549364","https://openalex.org/W2606313559","https://openalex.org/W3129185960","https://openalex.org/W6922135800","https://openalex.org/W3025612414","https://openalex.org/W7024138083"],"abstract_inverted_index":{"Many":[0],"problems":[1,183],"in":[2,57,102,123,152],"data":[3],"science":[4],"can":[5],"be":[6],"treated":[7],"as":[8,45,83,85,185],"estimating":[9],"a":[10,40,115,138,180],"low-rank":[11,31,91,187],"matrix":[12,27,32,188],"from":[13,65],"highly":[14],"incomplete,":[15],"sometimes":[16],"even":[17,151],"corrupted,":[18],"observations.":[19],"One":[20],"popular":[21],"approach":[22,163],"is":[23,97,133,142],"to":[24,26,100,113,135],"resort":[25],"factorization,":[28],"where":[29,70],"the":[30,46,60,71,81,86,90,94,103,125,148,153,159,165],"factors":[33],"are":[34],"optimized":[35],"via":[36],"first-order":[37],"methods":[38,112],"over":[39],"smooth":[41,62,95],"loss":[42],"function,":[43],"such":[44,184],"residual":[47,126],"sum":[48,127],"of":[49,68,74,89,117,128,147,155,161,182],"squares.":[50],"While":[51],"tremendous":[52],"progresses":[53],"have":[54],"been":[55],"made":[56],"recent":[58],"years,":[59],"natural":[61],"formulation":[63,96],"suffers":[64],"two":[66],"sources":[67],"ill-conditioning,":[69],"iteration":[72],"complexity":[73],"gradient":[75],"descent":[76],"scales":[77],"poorly":[78],"both":[79],"with":[80],"dimension":[82],"well":[84],"condition":[87,149],"number":[88],"matrix.":[92],"Moreover,":[93],"not":[98],"robust":[99,186],"corruptions":[101],"measurements.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108],"propose":[109],"scaled":[110],"subgradient":[111],"minimize":[114],"family":[116],"nonsmooth":[118],"and":[119,145,174,190],"nonconvex":[120],"formulations":[121],"\u2013":[122,131],"particular,":[124],"absolute":[129],"errors":[130],"which":[132],"guaranteed":[134],"converge":[136],"at":[137],"fast":[139],"rate":[140],"that":[141],"almost":[143],"dimension-free":[144],"independent":[146],"number,":[150],"presence":[154],"corruptions.":[156],"We":[157],"illustrate":[158],"effectiveness":[160],"our":[162],"when":[164],"observation":[166],"operator":[167],"satisfies":[168],"certain":[169],"mixed-norm":[170],"restricted":[171],"isometry":[172],"properties,":[173],"derive":[175],"state-of-the-art":[176],"performance":[177],"guarantees":[178],"for":[179],"variety":[181],"sensing":[189],"quadratic":[191],"sampling.":[192]},"counts_by_year":[{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2020-10-29T00:00:00"}