{"id":"https://openalex.org/W7161727497","doi":"https://doi.org/10.1109/tnse.2026.3695143","title":"Near-Optimal Reinforcement Learning With Shuffle Differential Privacy","display_name":"Near-Optimal Reinforcement Learning With Shuffle Differential Privacy","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161727497","doi":"https://doi.org/10.1109/tnse.2026.3695143"},"language":"en","primary_location":{"id":"doi:10.1109/tnse.2026.3695143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2026.3695143","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Network Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://curis.ku.dk/ws/files/559179406/Near-Optimal_Reinforcement.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037832036","display_name":"Shaojie Bai","orcid":"https://orcid.org/0009-0006-7526-5216"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojie Bai","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7434-8841","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136482577","display_name":"Mohammad Sadegh Talebi","orcid":null},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mohammad Sadegh Talebi","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-1934-7421","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136470124","display_name":"Chengcheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengcheng Zhao","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6816-6459","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136476024","display_name":"Peng Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Cheng","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4221-2162","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136472960","display_name":"Jiming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiming Chen","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3155-3145","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61307809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"9807","last_page":"9826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.44530001282691956,"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":0.44530001282691956,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3571999967098236,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.03819999843835831,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision 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":0.7272999882698059},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5794000029563904},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.37610000371932983},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.35530000925064087},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.3456999957561493}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7272999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502000093460083},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5794000029563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnse.2026.3695143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2026.3695143","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Network Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/ca7a5f0b-7e05-4ca4-abe6-1d3d0af08c2e","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/ca7a5f0b-7e05-4ca4-abe6-1d3d0af08c2e","pdf_url":"https://curis.ku.dk/ws/files/559179406/Near-Optimal_Reinforcement.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bai , S , Talebi , M S , Zhao , C , Cheng , P & Chen , J 2026 , ' Near-Optimal Reinforcement Learning With Shuffle Differential Privacy ' , IEEE Transactions on Network Science and Engineering , vol. 13 , pp. 9807-9826 . https://doi.org/10.1109/TNSE.2026.3695143","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/ca7a5f0b-7e05-4ca4-abe6-1d3d0af08c2e","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/ca7a5f0b-7e05-4ca4-abe6-1d3d0af08c2e","pdf_url":"https://curis.ku.dk/ws/files/559179406/Near-Optimal_Reinforcement.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bai , S , Talebi , M S , Zhao , C , Cheng , P & Chen , J 2026 , ' Near-Optimal Reinforcement Learning With Shuffle Differential Privacy ' , IEEE Transactions on Network Science and Engineering , vol. 13 , pp. 9807-9826 . https://doi.org/10.1109/TNSE.2026.3695143","raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4416405623","display_name":null,"funder_award_id":"1063-00031B","funder_id":"https://openalex.org/F4320313796","funder_display_name":"Innovationsfonden"},{"id":"https://openalex.org/G4513079086","display_name":null,"funder_award_id":"62293511","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7161727497.pdf","grobid_xml":"https://content.openalex.org/works/W7161727497.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,35,157],"(RL)":[2],"is":[3,13,27],"a":[4,62,67,112,140,146,165,170],"powerful":[5],"tool":[6],"for":[7,53,85,130,210],"sequential":[8],"decision-making,":[9],"but":[10],"its":[11,21],"application":[12],"often":[14,56],"hindered":[15],"by":[16,94],"privacy":[17,45,50,109,155],"concerns":[18],"arising":[19],"from":[20,36],"sensitive":[22],"interaction":[23],"data.":[24],"This":[25,89,201],"challenge":[26],"particularly":[28],"acute":[29],"in":[30,214],"advanced":[31],"networked":[32,87,215],"systems,":[33],"where":[34],"operational":[37],"and":[38,145,156,195],"user":[39],"data":[40],"can":[41],"expose":[42],"systems":[43],"to":[44,149,177],"inference":[46],"attacks.":[47],"Existing":[48],"differential":[49],"(DP)":[51],"models":[52],"RL":[54,132],"are":[55],"inadequate:":[57],"the":[58,74,96,124,134,151,178,184,197,204,207],"centralized":[59,113,179],"model":[60,76,99,105,180,209],"requires":[61],"fully":[63],"trusted":[64],"server,":[65],"creating":[66],"single":[68],"point":[69],"of":[70,100,154,199,206],"failure":[71],"risk,":[72],"while":[73,181],"local":[75,185],"incurs":[77],"significant":[78],"performance":[79],"degradation":[80],"that":[81,106,162],"renders":[82],"it":[83],"unsuitable":[84],"many":[86],"applications.":[88],"paper":[90],"addresses":[91],"this":[92],"gap":[93],"leveraging":[95],"emerging":[97],"shuffle":[98,135,208],"privacy,":[101],"an":[102],"intermediate":[103],"trust":[104,114],"provides":[107],"strong":[108],"guarantees":[110],"without":[111],"assumption.":[115],"We":[116],"present":[117],"Shuffle":[118],"Differentially":[119],"Private":[120],"Policy":[121],"Elimination":[122],"(SDP-PE),":[123],"first":[125],"generic":[126],"policy":[127],"elimination-based":[128],"algorithm":[129],"episodic":[131],"under":[133],"model.":[136,186],"Our":[137,159],"method":[138],"introduces":[139],"novel":[141],"exponential":[142],"batching":[143],"schedule":[144],"\u201cforgetting\u201d":[147],"mechanism":[148],"balance":[150],"competing":[152],"demands":[153],"performance.":[158],"analysis":[160],"shows":[161],"SDP-PE":[163],"achieves":[164],"near-optimal":[166],"regret":[167],"bound,":[168],"demonstrating":[169],"superior":[171],"privacy-regret":[172],"trade-off":[173],"with":[174],"utility":[175],"comparable":[176],"significantly":[182],"outperforming":[183],"The":[187],"numerical":[188],"experiments":[189],"also":[190],"corroborate":[191],"our":[192],"theoretical":[193],"results":[194],"demonstrate":[196],"effectiveness":[198],"SDP-PE.":[200],"work":[202],"establishes":[203],"viability":[205],"secure":[211],"data-driven":[212],"decision-making":[213],"systems.":[216]},"counts_by_year":[],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2026-05-20T00:00:00"}