{"id":"https://openalex.org/W7130681895","doi":"https://doi.org/10.48550/arxiv.2602.17284","title":"Efficient privacy loss accounting for subsampling and random allocation","display_name":"Efficient privacy loss accounting for subsampling and random allocation","publication_year":2026,"publication_date":"2026-02-19","ids":{"openalex":"https://openalex.org/W7130681895","doi":"https://doi.org/10.48550/arxiv.2602.17284"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.17284","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Feldman, Vitaly","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Feldman, Vitaly","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021672897","display_name":"Moshe Shenfeld","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenfeld, Moshe","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"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":0.9679999947547913,"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":0.9679999947547913,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.009399999864399433,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.007000000216066837,"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/poisson-distribution","display_name":"Poisson distribution","score":0.6980999708175659},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5737000107765198},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5236999988555908},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.5156999826431274},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.47839999198913574}],"concepts":[{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.6980999708175659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6274999976158142},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5073999762535095},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C2985139394","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Sampling scheme","level":3,"score":0.3937000036239624},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2892000079154968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.17284","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.17284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.17284","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.17284","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"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":{"We":[0],"consider":[1],"the":[2,40,72,112,121,125,128,133,156,177,184],"privacy":[3,114,147,157,222,239],"amplification":[4],"properties":[5],"of":[6,29,42,78,98,140,161,197,229],"a":[7,12,25,227],"sampling":[8,33,80],"scheme":[9,34,81],"in":[10,17,39,108,124,146],"which":[11,141,244],"user's":[13],"data":[14],"is":[15,190,204],"used":[16,145],"$k$":[18],"steps":[19,123],"chosen":[20],"randomly":[21],"and":[22,54],"uniformly":[23],"from":[24],"sequence":[26],"(or":[27],"set)":[28],"$t$":[30],"steps.":[31],"This":[32,232],"has":[35],"been":[36],"recently":[37],"applied":[38,164,175],"context":[41],"differentially":[43,167],"private":[44,57,168],"optimization":[45],"(Chua":[46],"et":[47,51,60,87],"al.,":[48,52,61,88],"2024a;":[49],"Choquette-Choo":[50],"2025)":[53,89],"communication-efficient":[55],"high-dimensional":[56],"aggregation":[58],"(Asi":[59],"2025),":[62],"where":[63],"it":[64],"was":[65],"shown":[66],"to":[67,91,96,120,165,176,236,242],"have":[68,103],"utility":[69],"advantages":[70],"over":[71],"standard":[73],"Poisson":[74,99,198],"sampling.":[75],"Theoretical":[76],"analyses":[77],"this":[79,151],"(Feldman":[82],"&":[83],"Shenfeld,":[84],"2025;":[85],"Dong":[86],"lead":[90],"bounds":[92],"that":[93,155,183,196],"are":[94,116,131],"close":[95],"those":[97],"sampling,":[100],"yet":[101],"still":[102],"two":[104],"significant":[105],"shortcomings.":[106],"First,":[107],"many":[109],"practical":[110],"settings,":[111],"resulting":[113],"parameters":[115,130],"not":[117],"tight":[118],"due":[119],"approximation":[122],"analysis.":[126,249],"Second,":[127],"computed":[129,172],"either":[132],"hockey":[134],"stick":[135],"or":[136],"Renyi":[137],"divergence,":[138],"both":[139],"introduce":[142],"overheads":[143],"when":[144],"loss":[148,158,223,240],"accounting.":[149],"In":[150,200],"work,":[152],"we":[153],"demonstrate":[154,182],"distribution":[159],"(PLD)":[160],"random":[162,188,202],"allocation":[163,189,203],"any":[166],"algorithm":[169],"can":[170],"be":[171],"efficiently.":[173],"When":[174],"Gaussian":[178],"mechanism,":[179],"our":[180,215],"results":[181],"privacy-utility":[185],"trade-off":[186],"for":[187,207,220],"at":[191],"least":[192],"as":[193,195],"good":[194],"subsampling.":[199],"particular,":[201],"better":[205],"suited":[206],"training":[208],"via":[209],"DP-SGD.":[210],"To":[211],"support":[212],"these":[213],"computations,":[214],"work":[216],"develops":[217],"new":[218],"tools":[219],"general":[221],"accounting":[224,241],"based":[225],"on":[226],"notion":[228,233],"PLD":[230],"realization.":[231],"allows":[234],"us":[235],"extend":[237],"accurate":[238],"subsampling":[243],"previously":[245],"required":[246],"manual":[247],"noise-mechanism-specific":[248]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-21T00:00:00"}