{"id":"https://openalex.org/W4401687089","doi":"https://doi.org/10.1109/isit57864.2024.10619114","title":"Training Generative Models from Privatized Data via Entropic Optimal Transport","display_name":"Training Generative Models from Privatized Data via Entropic Optimal Transport","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4401687089","doi":"https://doi.org/10.1109/isit57864.2024.10619114"},"language":"en","primary_location":{"id":"doi:10.1109/isit57864.2024.10619114","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isit57864.2024.10619114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5002797487","display_name":"Daria Reshetova","orcid":"https://orcid.org/0009-0007-2161-0595"},"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":"Daria Reshetova","raw_affiliation_strings":["Stanford University,Department of Electrical Engineering,Stanford,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Electrical Engineering,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020190617","display_name":"Weining Chen","orcid":"https://orcid.org/0000-0001-7355-9487"},"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":"Wei-Ning Chen","raw_affiliation_strings":["Stanford University,Department of Electrical Engineering,Stanford,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Electrical Engineering,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003322209","display_name":"Ayfer \u00d6zg\u00fcr","orcid":"https://orcid.org/0000-0002-4455-4692"},"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":"Ayfer \u00d6zg\u00fcr","raw_affiliation_strings":["Stanford University,Department of Electrical Engineering,Stanford,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Electrical Engineering,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.2986,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63432098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"605","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.7153000235557556,"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":0.7153000235557556,"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/training","display_name":"Training (meteorology)","score":0.7155835628509521},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6407495737075806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5708935260772705},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4802177846431732},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44658616185188293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3924025595188141},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35129109025001526},{"id":"https://openalex.org/keywords/meteorology","display_name":"Meteorology","score":0.15509432554244995},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08883479237556458}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7155835628509521},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6407495737075806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5708935260772705},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4802177846431732},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44658616185188293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3924025595188141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35129109025001526},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.15509432554244995},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08883479237556458}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit57864.2024.10619114","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isit57864.2024.10619114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6332318640","display_name":null,"funder_award_id":"#CCF-2213223","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1557833142","https://openalex.org/W1873763122","https://openalex.org/W2245160765","https://openalex.org/W2604272474","https://openalex.org/W2789226849","https://openalex.org/W2794511224","https://openalex.org/W2963527517","https://openalex.org/W2975364676","https://openalex.org/W3008527562","https://openalex.org/W3104110119","https://openalex.org/W3196859439","https://openalex.org/W3213415000","https://openalex.org/W4205228770","https://openalex.org/W4206471589","https://openalex.org/W4212774754","https://openalex.org/W4312453532","https://openalex.org/W4366083659","https://openalex.org/W4385535562","https://openalex.org/W4401462673"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4394050964","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Local":[0],"differential":[1],"privacy":[2],"is":[3],"a":[4,16,37],"powerful":[5],"method":[6,40],"for":[7,18,49],"privacy-preserving":[8],"data":[9,62],"collection.":[10],"In":[11],"this":[12,80],"paper,":[13],"we":[14],"develop":[15],"framework":[17],"training":[19],"Generative":[20],"Adversarial":[21],"Networks":[22],"(GANs)":[23],"on":[24],"differentially":[25],"privatized":[26,71],"data.":[27],"We":[28,73],"show":[29],"that":[30,44,75,92],"entropic":[31,93],"regularization":[32,39,94],"of":[33,95,102,106,112,127],"optimal":[34,96],"transport":[35,97],"-":[36,53],"popular":[38],"in":[41,114,123],"the":[42,55,59,77,87,100,104,110,124,128],"literature":[43],"has":[45,68],"often":[46],"been":[47],"leveraged":[48],"its":[50],"computational":[51],"benefits":[52],"enables":[54,99],"generator":[56],"to":[57,70,82],"learn":[58],"raw":[60],"(unprivatized)":[61],"distribution":[63],"even":[64],"though":[65],"it":[66],"only":[67],"access":[69],"samples.":[72],"prove":[74],"at":[76,86],"same":[78],"time":[79],"leads":[81],"fast":[83],"statistical":[84,115],"convergence":[85],"parametric":[88],"rate.":[89],"This":[90],"shows":[91],"uniquely":[98],"mitigation":[101],"both":[103],"effects":[105],"privatization":[107],"noise":[108],"and":[109],"curse":[111],"dimensionality":[113],"convergence.":[116],"The":[117],"omitted":[118],"proofs":[119],"can":[120],"be":[121],"found":[122],"full":[125],"version":[126],"paper":[129],"https://arxiv.org/abs/2306.09547":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}