{"id":"https://openalex.org/W2963780177","doi":"https://doi.org/10.1109/tit.2014.2323359","title":"The Optimal Hard Threshold for Singular Values is <inline-formula> <tex-math notation=\"TeX\">\\(4/\\sqrt {3}\\) </tex-math></inline-formula>","display_name":"The Optimal Hard Threshold for Singular Values is <inline-formula> <tex-math notation=\"TeX\">\\(4/\\sqrt {3}\\) </tex-math></inline-formula>","publication_year":2014,"publication_date":"2014-06-30","ids":{"openalex":"https://openalex.org/W2963780177","doi":"https://doi.org/10.1109/tit.2014.2323359","mag":"2963780177"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2014.2323359","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tit.2014.2323359","pdf_url":"https://ieeexplore.ieee.org/ielx7/18/6851961/06846297.pdf","source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/18/6851961/06846297.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013235677","display_name":"Matan Gavish","orcid":"https://orcid.org/0000-0001-6747-6888"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matan Gavish","raw_affiliation_strings":["Department of Statistics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065355421","display_name":"David L. Donoho","orcid":"https://orcid.org/0000-0003-1830-710X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David L. Donoho","raw_affiliation_strings":["Department of Statistics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013235677"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":27.6802,"has_fulltext":false,"cited_by_count":666,"citation_normalized_percentile":{"value":0.99886973,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"60","issue":"8","first_page":"5040","last_page":"5053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":1.0,"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":1.0,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11716","display_name":"Random Matrices and Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"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/mathematics","display_name":"Mathematics","score":0.6977621912956238},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.6802655458450317},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6754981279373169},{"id":"https://openalex.org/keywords/singular-value","display_name":"Singular value","score":0.6676696538925171},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.6262134313583374},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6019898653030396},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5286158919334412},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41180023550987244},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.38941431045532227},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.337787389755249},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.32399827241897583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.1440284252166748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12291222810745239},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.11666026711463928}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6977621912956238},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.6802655458450317},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6754981279373169},{"id":"https://openalex.org/C109282560","wikidata":"https://www.wikidata.org/wiki/Q4166054","display_name":"Singular value","level":3,"score":0.6676696538925171},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.6262134313583374},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6019898653030396},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5286158919334412},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41180023550987244},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.38941431045532227},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.337787389755249},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32399827241897583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.1440284252166748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12291222810745239},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.11666026711463928},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2014.2323359","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tit.2014.2323359","pdf_url":"https://ieeexplore.ieee.org/ielx7/18/6851961/06846297.pdf","source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tit.2014.2323359","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tit.2014.2323359","pdf_url":"https://ieeexplore.ieee.org/ielx7/18/6851961/06846297.pdf","source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963780177.pdf","grobid_xml":"https://content.openalex.org/works/W2963780177.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1520752838","https://openalex.org/W1525046419","https://openalex.org/W1548938959","https://openalex.org/W1586554030","https://openalex.org/W1971913428","https://openalex.org/W1981573335","https://openalex.org/W1996023858","https://openalex.org/W2000157792","https://openalex.org/W2000345836","https://openalex.org/W2004026774","https://openalex.org/W2005051528","https://openalex.org/W2005423095","https://openalex.org/W2021680564","https://openalex.org/W2042283504","https://openalex.org/W2045547832","https://openalex.org/W2063942101","https://openalex.org/W2072974424","https://openalex.org/W2081940622","https://openalex.org/W2086486316","https://openalex.org/W2089794108","https://openalex.org/W2098056745","https://openalex.org/W2103972604","https://openalex.org/W2123226256","https://openalex.org/W2130121108","https://openalex.org/W2132657058","https://openalex.org/W2133097426","https://openalex.org/W2144730813","https://openalex.org/W2148541040","https://openalex.org/W2148654450","https://openalex.org/W2157195543","https://openalex.org/W2157752701","https://openalex.org/W2158044763","https://openalex.org/W2186714580","https://openalex.org/W2950070173","https://openalex.org/W3098139351","https://openalex.org/W3099609308","https://openalex.org/W3104577407","https://openalex.org/W4285719527","https://openalex.org/W4300848269","https://openalex.org/W6632841770","https://openalex.org/W6662118774","https://openalex.org/W6679166778","https://openalex.org/W6686626303"],"related_works":["https://openalex.org/W4319586039","https://openalex.org/W4382583540","https://openalex.org/W1607100495","https://openalex.org/W2147072251","https://openalex.org/W1990844505","https://openalex.org/W2148568324","https://openalex.org/W4386721910","https://openalex.org/W4378770618","https://openalex.org/W2164147222","https://openalex.org/W2038393145"],"abstract_inverted_index":{"We":[0,28],"consider":[1],"recovery":[2],"of":[3,12,49,59,68,74,80,185,205,240],"low-rank":[4,61,187],"matrices":[5,120,284],"from":[6],"noisy":[7],"data":[8,242],"by":[9,118,224,237],"hard":[10,69,162,270,275],"thresholding":[11,126,143,163,195,231],"singular":[13,18,113,175,228,243],"values,":[14],"in":[15,36,71,77,153,310],"which":[16,179],"empirical":[17,112],"values":[19,244],"below":[20],"a":[21,37],"threshold":[22,271],"\u03bb":[23],"are":[24,131,190,245],"set":[25],"to":[26,52,146,192,200],"0.":[27],"study":[29],"the":[30,40,47,50,56,60,72,110,125,182,186,197,221,233,241,277],"asymptotic":[31],"mean":[32],"squared":[33],"error":[34],"(AMSE)":[35],"framework,":[38],"where":[39,104],"matrix":[41,51,76,188,204],"size":[42],"is":[43,83,90,102,109,158,169],"large":[44],"compared":[45],"with":[46,121,133,285],"rank":[48,148,184,206],"be":[53,303],"recovered,":[54],"and":[55,129,149,168,232,258,297],"signal-to-noise":[57],"ratio":[58],"piece":[62],"stays":[63],"constant.":[64],"The":[65,266],"AMSE-optimal":[66],"choice":[67],"threshold,":[70],"case":[73],"n-by-n":[75,203],"white":[78],"noise":[79,151,307],"level":[81,152],"\u03c3,":[82],"simply":[84,93],"(4/\u221a3)\u221an\u03c3":[85],"\u2248":[86],"2.309\u221an\u03c3":[87],"when":[88,100],"\u03c3":[89,101],"known,":[91],"or":[92],"2.858":[94,130],"\u00b7":[95],"y":[96,105],"med":[99,108],"unknown,":[103],"median":[111],"value.":[114],"For":[115],"nonsquare,":[116],"m":[117,122],"n":[119,124],"\u2260":[123],"coefficients":[127],"4/\u221a3":[128],"replaced":[132],"different":[134,306],"provided":[135,223],"constants":[136],"that":[137,292],"depend":[138],"on":[139],"m/n.":[140],"Asymptotically,":[141],"this":[142],"rule":[144],"adapts":[145],"unknown":[147,150],"an":[154,202,209],"optimal":[155],"manner:":[156],"it":[157],"always":[159,170],"better":[160,171],"than":[161,172],"at":[164,181,196,211],"any":[165,238],"other":[166,298],"value,":[167],"ideal":[173],"truncated":[174],"value":[176,199,229,268],"decomposition":[177],"(TSVD),":[178],"truncates":[180],"true":[183],"we":[189],"trying":[191],"recover.":[193],"Hard":[194],"recommended":[198,267],"recover":[201],"r":[207],"guarantees":[208,222,281],"AMSE":[210,280],"most":[212],"3":[213],"nr\u03c3":[214,247,253,260],"2":[217,250,256,263],".":[218],"In":[219],"comparison,":[220],"TSVD,":[225],"optimally":[226],"tuned":[227],"soft":[230],"best":[234,278],"guarantee":[235],"achievable":[236],"shrinkage":[239,300],"5":[246],",":[251,257,264],"6":[252],"2":[259],"respectively.":[265],"for":[269,282,305],"also":[272],"offers,":[273],"among":[274],"thresholds,":[276],"possible":[279],"recovering":[283],"bounded":[286],"nuclear":[287],"norm.":[288],"Empirical":[289],"evidence":[290],"suggests":[291],"performance":[293],"improvement":[294],"over":[295],"TSVD":[296],"popular":[299],"rules":[301],"can":[302],"substantial,":[304],"distributions,":[308],"even":[309],"relatively":[311],"small":[312],"n.":[313]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":88},{"year":2023,"cited_by_count":75},{"year":2022,"cited_by_count":55},{"year":2021,"cited_by_count":84},{"year":2020,"cited_by_count":81},{"year":2019,"cited_by_count":65},{"year":2018,"cited_by_count":41},{"year":2017,"cited_by_count":29},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2025-10-10T00:00:00"}