{"id":"https://openalex.org/W7214991969","doi":"https://doi.org/10.48550/arxiv.2609.36678","title":"Understanding Private Evolution as Learning-Augmented Clustering","display_name":"Understanding Private Evolution as Learning-Augmented Clustering","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214991969","doi":"https://doi.org/10.48550/arxiv.2609.36678"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36678","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36678","pdf_url":"https://arxiv.org/pdf/2609.36678","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.36678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004893242","display_name":"Audra McMillan","orcid":"https://orcid.org/0000-0003-4231-6110","observed_orcids":["https://orcid.org/0000-0003-4231-6110"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McMillan, Audra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080065269","display_name":"Kunal Talwar","orcid":"https://orcid.org/0009-0000-5661-3541","observed_orcids":["https://orcid.org/0009-0000-5661-3541"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Talwar, Kunal","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153587230","display_name":"Felix Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Felix","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.9922000169754028,"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":0.9922000169754028,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.0013000000035390258,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.000699999975040555,"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/differential-privacy","display_name":"differential privacy","score":0.8840000033378601},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.9769999980926514},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.9340000152587891},{"id":"https://openalex.org/keywords/clustering","display_name":"clustering","score":0.5540000200271606},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.8560000061988831},{"id":"https://openalex.org/keywords/intrinsic-dimension","display_name":"intrinsic dimension","score":0.9369999766349792},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.8009999990463257},{"id":"https://openalex.org/keywords/privacy-preserving-data-synthesis","display_name":"privacy-preserving data synthesis","score":0.503000020980835}],"concepts":[{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6564000248908997},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6269000172615051},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5504999756813049},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5437999963760376},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3743000030517578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36678","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36678","pdf_url":"https://arxiv.org/pdf/2609.36678","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.2609.36678","doi":"https://doi.org/10.48550/arxiv.2609.36678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36678","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:2609.36678","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36678","pdf_url":"https://arxiv.org/pdf/2609.36678","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214991969.pdf","grobid_xml":"https://content.openalex.org/works/W7214991969.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2787877872","https://openalex.org/W3098480654","https://openalex.org/W4379474720","https://openalex.org/W4407359145","https://openalex.org/W4407384905","https://openalex.org/W4415090745","https://openalex.org/W4417132897","https://openalex.org/W4417136690","https://openalex.org/W4417538991"],"related_works":["https://openalex.org/W4417136690","https://openalex.org/W7163176847","https://openalex.org/W6977602458","https://openalex.org/W4320837448","https://openalex.org/W3100761535","https://openalex.org/W7223348900","https://openalex.org/W7214785150","https://openalex.org/W3175638203","https://openalex.org/W4417095775","https://openalex.org/W7056018300"],"abstract_inverted_index":{"Private":[0],"Evolution":[1],"(PE)":[2],"is":[3,58,136],"a":[4,18,54,117],"differentially":[5],"private":[6],"algorithm":[7,135],"for":[8],"synthetic":[9],"data":[10],"generation.":[11],"While":[12],"it":[13,22],"can":[14,69,107,142],"be":[15],"viewed":[16],"as":[17,37,87],"Wasserstein":[19,30,40],"learning":[20],"algorithm,":[21],"performs":[23],"much":[24,71],"better":[25,72],"in":[26,82],"practice":[27],"than":[28],"worst-case":[29],"analyses":[31],"would":[32],"predict.":[33],"We":[34,42,99],"recast":[35],"PE":[36,106,122],"generative":[38,55],"model-augmented":[39],"learning.":[41],"show":[43,101,131],"theoretically":[44],"that":[45,57,102,132],"when":[46],"we":[47,68,130],"take":[48],"into":[49],"account":[50],"the":[51,64,78,83,88],"use":[52],"of":[53,105,121],"model":[56],"able":[59],"to":[60,109],"capture":[61],"something":[62],"about":[63],"true":[65],"distribution,":[66,89],"then":[67,90],"obtain":[70],"performance":[73],"bounds.":[74],"For":[75],"example,":[76],"if":[77],"generator":[79],"gives":[80],"samples":[81],"same":[84],"low-dimensional":[85],"space":[86],"sample":[91],"complexity":[92],"depends":[93],"on":[94,111,126],"intrinsic,":[95],"not":[96],"ambient,":[97],"dimension.":[98],"also":[100],"standard":[103,139],"variants":[104],"fail":[108],"converge":[110],"simple":[112],"well-clustered":[113],"instances,":[114],"and":[115,141],"propose":[116],"new":[118,134],"geometry-aware":[119],"version":[120],"with":[123,138],"provable":[124],"convergence":[125],"such":[127],"instances.":[128],"Experimentally,":[129],"our":[133],"competitive":[137],"baselines":[140],"improve":[143],"recall.":[144]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}