{"id":"https://openalex.org/W4290845189","doi":"https://doi.org/10.48550/arxiv.2107.05824","title":"Covariance's Loss is Privacy's Gain: Computationally Efficient, Private and Accurate Synthetic Data","display_name":"Covariance's Loss is Privacy's Gain: Computationally Efficient, Private and Accurate Synthetic Data","publication_year":2021,"publication_date":"2021-07-13","ids":{"openalex":"https://openalex.org/W4290845189","doi":"https://doi.org/10.48550/arxiv.2107.05824"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2107.05824","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05824","pdf_url":"https://arxiv.org/pdf/2107.05824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.05824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034076533","display_name":"March T. Boedihardjo","orcid":"https://orcid.org/0000-0003-4969-0586","observed_orcids":["https://orcid.org/0000-0003-4969-0586"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Boedihardjo, March","raw_affiliation_strings":["Department of Mathematics , ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080565728","display_name":"Thomas Strohmer","orcid":"https://orcid.org/0000-0003-2029-3317","observed_orcids":["https://orcid.org/0000-0003-2029-3317"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Strohmer, Thomas","raw_affiliation_strings":["Center of Data Science and Artificial Intelligence Research and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Data Science and Artificial Intelligence Research and","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070281692","display_name":"Roman Vershynin","orcid":"https://orcid.org/0009-0008-4718-7788","observed_orcids":["https://orcid.org/0009-0008-4718-7788"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vershynin, Roman","raw_affiliation_strings":["Department of Mathematics , University of California Davis","Department of Mathematics , University of California Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , University of California Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Department of Mathematics , University of California Irvine","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":1.0,"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":1.0,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/synthetic-data-generation","display_name":"synthetic data generation","score":0.8840000033378601},{"id":"https://openalex.org/keywords/privacy-preserving-data-publishing","display_name":"privacy-preserving data publishing","score":0.9160000085830688},{"id":"https://openalex.org/keywords/conditional-expectation","display_name":"conditional expectation","score":0.9190000295639038},{"id":"https://openalex.org/keywords/microaggregation","display_name":"microaggregation","score":0.9269999861717224},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.9330000281333923},{"id":"https://openalex.org/keywords/anonymity","display_name":"anonymity","score":0.5699999928474426},{"id":"https://openalex.org/keywords/privacy-utility-trade-off","display_name":"privacy-utility trade-off","score":0.8569999933242798},{"id":"https://openalex.org/keywords/np-hard-problems","display_name":"NP-hard problems","score":0.7540000081062317},{"id":"https://openalex.org/keywords/data-utility","display_name":"data utility","score":0.4490000009536743},{"id":"https://openalex.org/keywords/information-loss","display_name":"information loss","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.9302841424942017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385702133178711},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.6256654858589172},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.549502968788147},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5411936044692993},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5224320292472839},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.49618133902549744},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.46258804202079773},{"id":"https://openalex.org/C2777706471","wikidata":"https://www.wikidata.org/wiki/Q17061432","display_name":"k-anonymity","level":3,"score":0.4483812153339386},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39127781987190247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25854548811912537},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22454461455345154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20285969972610474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19046330451965332},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17022275924682617},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2107.05824","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05824","pdf_url":"https://arxiv.org/pdf/2107.05824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2107.05824","doi":"https://doi.org/10.48550/arxiv.2107.05824","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.05824","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.05824","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05824","pdf_url":"https://arxiv.org/pdf/2107.05824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G156548516","display_name":"ATD: A Mathematical Framework for Generating Synthetic Data","funder_award_id":"2027248","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3777448576","display_name":"ATD: Multimode Machine Learning and Deep GeoNetworks for Anomaly Detection","funder_award_id":"1737943","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5173421202","display_name":"Operators on Banach Spaces","funder_award_id":"2140592","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8746953091","display_name":"Collaborative Research:  A Mathematical Framework for Generating Synthetic Data","funder_award_id":"2027299","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8945958279","display_name":"High-Dimensional Probability for High-Dimensional Data","funder_award_id":"1954233","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3196366209","https://openalex.org/W7198127854","https://openalex.org/W4313342281","https://openalex.org/W4312733257","https://openalex.org/W4414898861","https://openalex.org/W4411058948","https://openalex.org/W3177472190","https://openalex.org/W3116489338","https://openalex.org/W2910283416","https://openalex.org/W2995853232"],"abstract_inverted_index":{"The":[0,15],"protection":[1],"of":[2,6,37,108,127],"private":[3],"information":[4,144],"is":[5,58,68,90,145],"vital":[7],"importance":[8],"in":[9,25,122],"data-driven":[10],"research,":[11],"business,":[12],"and":[13,19,29,52,98,136,177],"government.":[14],"conflict":[16],"between":[17],"privacy":[18,67,96],"utility":[20],"has":[21],"triggered":[22],"intensive":[23],"research":[24],"the":[26,44,64,79,125,140],"computer":[27],"science":[28],"statistics":[30],"communities,":[31],"who":[32],"have":[33,48],"developed":[34],"a":[35,84,105,113,116,133],"variety":[36],"methods":[38],"for":[39],"privacy-preserving":[40],"data":[41,86,101],"release.":[42],"Among":[43],"main":[45],"concepts":[46],"that":[47,89,161],"emerged":[49],"are":[50],"anonymity":[51],"differential":[53],"privacy.":[54],"Today,":[55],"another":[56],"solution":[57],"gaining":[59],"traction,":[60],"synthetic":[61,85,178],"data.":[62,179],"However,":[63],"road":[65],"to":[66,82,139,164,170],"paved":[69],"with":[70,94],"NP-hard":[71,80],"problems.":[72],"In":[73],"this":[74,109,153],"paper":[75],"we":[76,131,148],"focus":[77],"on":[78],"challenge":[81],"develop":[83],"generation":[87],"method":[88],"computationally":[91],"efficient,":[92],"comes":[93],"provable":[95],"guarantees,":[97],"rigorously":[99],"quantifies":[100],"utility.":[102],"We":[103],"solve":[104],"relaxed":[106],"version":[107],"problem":[110,121],"by":[111],"studying":[112],"fundamental,":[114],"but":[115],"first":[117],"glance":[118],"completely":[119],"unrelated,":[120],"probability":[123,157],"concerning":[124,174],"concept":[126],"covariance":[128],"loss.":[129],"Namely,":[130],"find":[132],"nearly":[134],"optimal":[135,168],"constructive":[137],"answer":[138],"question":[141],"how":[142],"much":[143],"lost":[146],"when":[147],"take":[149],"conditional":[150],"expectation.":[151],"Surprisingly,":[152],"excursion":[154],"into":[155],"theoretical":[156],"produces":[158],"mathematical":[159],"techniques":[160],"allow":[162],"us":[163],"derive":[165],"constructive,":[166],"approximately":[167],"solutions":[169],"difficult":[171],"applied":[172],"problems":[173],"microaggregation,":[175],"privacy,":[176]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2022-08-12T00:00:00"}