{"id":"https://openalex.org/W4417232241","doi":"https://doi.org/10.1002/sam.70053","title":"Robust and Differentially Private Principal Component Analysis","display_name":"Robust and Differentially Private Principal Component Analysis","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417232241","doi":"https://doi.org/10.1002/sam.70053"},"language":"en","primary_location":{"id":"doi:10.1002/sam.70053","is_oa":true,"landing_page_url":"https://doi.org/10.1002/sam.70053","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/sam.70053","source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: An ASA Data Science Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/sam.70053","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Minwoo Kim","orcid":"https://orcid.org/0009-0007-3220-6504"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minwoo Kim","raw_affiliation_strings":["Department of Statistics Seoul National University  Seoul South Korea","Department of Statistics, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-3220-6504","affiliations":[{"raw_affiliation_string":"Department of Statistics Seoul National University  Seoul South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Statistics, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018954610","display_name":"Sungkyu Jung","orcid":"https://orcid.org/0000-0002-6023-8956"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sungkyu Jung","raw_affiliation_strings":["Department of Statistics Seoul National University  Seoul South Korea","Institute for Data Innovation in Science Seoul National University  Seoul South Korea","Department of Statistics, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6023-8956","affiliations":[{"raw_affiliation_string":"Department of Statistics Seoul National University  Seoul South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Institute for Data Innovation in Science Seoul National University  Seoul South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Statistics, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018954610"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":3760,"currency":"USD","value_usd":3760},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19348798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.798799991607666,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.798799991607666,"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/T11716","display_name":"Random Matrices and Applications","score":0.0869000032544136,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.034699998795986176,"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/principal-component-analysis","display_name":"Principal component analysis","score":0.8299000263214111},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7379999756813049},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5817000269889832},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5652999877929688},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5540000200271606},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5414000153541565},{"id":"https://openalex.org/keywords/sparse-pca","display_name":"Sparse PCA","score":0.47940000891685486},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.4652999937534332},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44839999079704285},{"id":"https://openalex.org/keywords/robust-principal-component-analysis","display_name":"Robust principal component analysis","score":0.43290001153945923}],"concepts":[{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.8299000263214111},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7379999756813049},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5318999886512756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5099999904632568},{"id":"https://openalex.org/C24252448","wikidata":"https://www.wikidata.org/wiki/Q7573786","display_name":"Sparse PCA","level":3,"score":0.47940000891685486},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.43290001153945923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42899999022483826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40560001134872437},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.3614000082015991},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C71176878","wikidata":"https://www.wikidata.org/wiki/Q17014987","display_name":"Functional principal component analysis","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C74887250","wikidata":"https://www.wikidata.org/wiki/Q3455892","display_name":"Principal component regression","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/sam.70053","is_oa":true,"landing_page_url":"https://doi.org/10.1002/sam.70053","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/sam.70053","source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: An ASA Data Science Journal","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1002/sam.70053","is_oa":true,"landing_page_url":"https://doi.org/10.1002/sam.70053","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/sam.70053","source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: An ASA Data Science Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2806633837","display_name":null,"funder_award_id":"RS-2024-00333399","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3149324952","display_name":null,"funder_award_id":"RS-2023-00218231","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4308274077","display_name":null,"funder_award_id":"RS-2023-00301976","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7385613323","display_name":null,"funder_award_id":"RS-2023-00301976","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8779578172","display_name":null,"funder_award_id":"RS-2023-00218231","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417232241.pdf","grobid_xml":"https://content.openalex.org/works/W4417232241.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W44394327","https://openalex.org/W170820490","https://openalex.org/W1811453145","https://openalex.org/W1873763122","https://openalex.org/W1939766099","https://openalex.org/W1981469185","https://openalex.org/W1997690112","https://openalex.org/W2088911135","https://openalex.org/W2089893077","https://openalex.org/W2123820077","https://openalex.org/W2133148918","https://openalex.org/W2138865266","https://openalex.org/W2150136439","https://openalex.org/W2473418344","https://openalex.org/W2594311007","https://openalex.org/W2798548367","https://openalex.org/W2963699739","https://openalex.org/W4205228770","https://openalex.org/W4213278605","https://openalex.org/W4250954493","https://openalex.org/W4302324459","https://openalex.org/W4391382837","https://openalex.org/W4392289662","https://openalex.org/W4393116103","https://openalex.org/W4403523907","https://openalex.org/W4407926546"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"Recent":[1],"advances":[2],"have":[3],"sparked":[4],"significant":[5],"interest":[6],"in":[7,116,165,171],"the":[8,80,83,137,146,150],"development":[9],"of":[10,86,113,136,167],"privacy\u2010preserving":[11,58],"Principal":[12],"Component":[13],"Analysis":[14],"(PCA).":[15],"However,":[16],"many":[17],"existing":[18,163],"approaches":[19,164],"rely":[20],"on":[21,43,141],"restrictive":[22],"assumptions,":[23],"such":[24],"as":[25],"assuming":[26],"sub\u2010Gaussian":[27],"data":[28,33,55,89,126,175],"or":[29,41,173],"being":[30],"vulnerable":[31],"to":[32,71,144],"contamination.":[34,127],"Additionally,":[35,121],"some":[36],"methods":[37],"are":[38],"computationally":[39],"expensive":[40],"depend":[42],"unknown":[44],"model":[45],"parameters":[46],"that":[47,82,158],"must":[48],"be":[49],"estimated,":[50],"limiting":[51],"their":[52,93],"accessibility":[53],"for":[54],"analysts":[56],"seeking":[57],"PCA.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,109],"propose":[64],"a":[65,106,117],"differentially":[66,118],"private":[67,119],"PCA":[68],"method":[69,160],"applicable":[70],"heavy\u2010tailed":[72,102],"and":[73,92,101,133],"potentially":[74],"contaminated":[75,174],"data.":[76],"Our":[77],"approach":[78],"leverages":[79],"property":[81],"covariance":[84],"matrix":[85],"properly":[87],"rescaled":[88],"preserves":[90],"eigenvectors":[91],"order":[94],"under":[95],"elliptical":[96],"distributions,":[97],"which":[98],"include":[99],"Gaussian":[100],"distributions.":[103],"By":[104],"applying":[105],"bounded":[107],"transformation,":[108],"enable":[110],"straightforward":[111],"computation":[112],"principal":[114,152],"components":[115],"manner.":[120],"boundedness":[122],"guarantees":[123],"robustness":[124],"against":[125],"We":[128],"conduct":[129],"both":[130],"theoretical":[131],"analysis":[132],"empirical":[134],"evaluations":[135],"proposed":[138],"method,":[139],"focusing":[140],"its":[142],"ability":[143],"recover":[145],"subspace":[147],"spanned":[148],"by":[149],"leading":[151],"components.":[153],"Extensive":[154],"numerical":[155],"experiments":[156],"demonstrate":[157],"our":[159],"consistently":[161],"outperforms":[162],"terms":[166],"statistical":[168],"utility,":[169],"particularly":[170],"non\u2010Gaussian":[172],"settings.":[176]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-12-11T00:00:00"}