{"id":"https://openalex.org/W7162147777","doi":"https://doi.org/10.48550/arxiv.2605.21601","title":"Near-Optimal Generalized Private Testing","display_name":"Near-Optimal Generalized Private Testing","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162147777","doi":"https://doi.org/10.48550/arxiv.2605.21601"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21601","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045318419","display_name":"Anamay Chaturvedi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaturvedi, Anamay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136174080","display_name":"Monika Henzinger","orcid":"https://orcid.org/0000-0002-5008-6530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henzinger, Monika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073803308","display_name":"Jalaj Upadhyay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Upadhyay, Jalaj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.8827999830245972,"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":0.8827999830245972,"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/T10237","display_name":"Cryptography and Data Security","score":0.05719999969005585,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.013199999928474426,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.6050999760627747},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5577999949455261},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5360999703407288},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5160999894142151},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.45399999618530273},{"id":"https://openalex.org/keywords/computerized-adaptive-testing","display_name":"Computerized adaptive testing","score":0.42260000109672546},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41100001335144043},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.40619999170303345}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5160999894142151},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4853000044822693},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C144352353","wikidata":"https://www.wikidata.org/wiki/Q2920411","display_name":"Computerized adaptive testing","level":3,"score":0.42260000109672546},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3984000086784363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C181447626","wikidata":"https://www.wikidata.org/wiki/Q1224359","display_name":"Differential item functioning","level":4,"score":0.33469998836517334},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C153517567","wikidata":"https://www.wikidata.org/wiki/Q26090","display_name":"Mechanism design","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21601","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21601","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"differential":[1],"privacy":[2],"(DP),":[3],"the":[4,31,35,54,87,94,104,122,141,168,179,185,191,200],"generalized":[5,110,219],"private":[6,89,111,220],"testing":[7,90,221],"problem":[8],"was":[9],"introduced":[10],"by":[11,53],"Liu":[12],"and":[13,23,58,77,115,130,163,226],"Talwar":[14],"(STOC":[15],"2019).":[16],"Given":[17],"a":[18,24,43,59,172,211],"dataset":[19],"$X":[20],"\\in":[21],"\\mathcal{X}$":[22],"sequence":[25,117],"of":[26,118,143,145,160,206],"black-box":[27,173],"$\\varepsilon_t$-DP":[28],"mechanisms":[29,120],"$M_t:\\mathcal{X}\\to\\{+1,-1\\}$,":[30],"analyst":[32],"must":[33],"accept":[34],"first":[36,192],"mechanism":[37],"whose":[38,92],"success":[39],"probability":[40,66,139],"$p_t=\\Pr[M_t(X)=+1]$":[41],"exceeds":[42],"given":[44],"threshold":[45,61],"$p^*\\in(0,1)$,":[46],"while":[47],"achieving":[48],"DP.":[49,101],"Accuracy":[50],"is":[51,75,83,98,124,147],"measured":[52],"gap":[55],"between":[56],"$p^*$":[57],"rejection":[60],"$\\bar{p}$,":[62],"such":[63],"that":[64],"with":[65],"$1-\u03b2$":[67],"for":[68,109,136,151,175,195,222],"all":[69,152],"$t\\geq1$,":[70],"if":[71,78],"$p_t\\leq\\bar{p}$,":[72],"then":[73,81],"$M_t$":[74,146],"rejected,":[76],"$p_t\\geq":[79],"p^*$,":[80],"it":[82],"accepted.":[84],"This":[85,188],"generalizes":[86],"standard":[88],"problem,":[91],"solution,":[93],"Sparse":[95],"Vector":[96],"Technique,":[97],"ubiquitous":[99],"in":[100,214],"We":[102],"introduce":[103],"Generalized":[105],"Thresholding":[106],"Mechanism":[107],"(GTM)":[108],"testing.":[112],"For":[113,127],"$\\varepsilon>0$":[114],"any":[116],"$(\\varepsilon_t,\u03b4_t)$-DP":[119],"$M_t$,":[121],"GTM":[123,201],"pure":[125],"$\\varepsilon$-DP.":[126],"$\u03b8>0$,":[128],"$\u03b3\\in(1,2]$,":[129],"$\u03b2\\in(0,1)$,":[131],"$\\bar{p}_t=\\max(p^*/\u03b3\u039b_t,":[132],"1":[133],"-":[134],"\u03b3\u039b_t(1-p^*))-\u03b4_t/\\varepsilon_t$":[135],"$\u039b_t=(5t\\ln^3(t+2))^{(2+\u03b8)\\varepsilon_t/\\varepsilon}(4/\u03b2)^{(3+\u03b8+2/\u03b8)\\varepsilon_t/\\varepsilon}$.":[137],"With":[138],"$1-\u03b2$,":[140],"number":[142],"evaluations":[144],"at":[148],"most":[149],"$O((\\ln(t/\u03b2)/(\u03b3-1)^2)\\max(\u039b_t/p^*,(1-p^*)^{-1}))$":[150],"$t\\geq":[153],"1$.":[154],"Our":[155],"lower":[156],"bounds":[157],"prove":[158],"near-optimality":[159],"our":[161],"accuracy":[162],"sample":[164],"complexity":[165],"guarantees.":[166],"Via":[167],"GTM,":[169],"we":[170],"give":[171],"reduction":[174],"DP":[176],"optimization":[177,224],"from":[178],"continual":[180],"observation":[181],"(CO)":[182],"setting":[183],"to":[184],"batch":[186],"setting.":[187],"gives":[189],"us":[190],"DP-CO":[193],"algorithms":[194],"many":[196],"maximization":[197],"problems.":[198],"Further,":[199],"permits":[202],"an":[203],"adaptive":[204],"choice":[205],"acceptance":[207],"thresholds":[208],"$(p^*_t)_{t\\geq1}$,":[209],"addressing":[210],"challenge":[212],"mentioned":[213],"prior":[215],"work":[216],"on":[217],"using":[218],"hyperparameter":[223],"(Papernot":[225],"Steinke":[227],"(ICLR":[228],"2022)).":[229]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-23T00:00:00"}