{"id":"https://openalex.org/W4321479941","doi":"https://doi.org/10.1145/3539597.3570470","title":"Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization","display_name":"Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321479941","doi":"https://doi.org/10.1145/3539597.3570470"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","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/A5103205628","display_name":"Canzhe Zhao","orcid":"https://orcid.org/0000-0003-1080-9412"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Canzhe Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1080-9412","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063722358","display_name":"Yanjie Ze","orcid":"https://orcid.org/0000-0001-8422-8923"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Ze","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8422-8923","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040325272","display_name":"J. Dong","orcid":"https://orcid.org/0000-0001-8579-306X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Dong","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8579-306X","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065857724","display_name":"Baoxiang Wang","orcid":"https://orcid.org/0000-0002-2997-0970"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoxiang Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2997-0970","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066355409","display_name":"Shuai Li","orcid":"https://orcid.org/0000-0002-3935-0708"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3935-0708","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62207258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"985","last_page":"993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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":0.9833999872207642,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.983299970626831,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7207694053649902},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.7132636904716492},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.616706132888794},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6066436767578125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5881919264793396},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5788669586181641},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5439921617507935},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5150746703147888},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.469757080078125},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4372773766517639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41609466075897217},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41104555130004883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3128548860549927},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28904157876968384}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7207694053649902},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7132636904716492},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.616706132888794},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6066436767578125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5881919264793396},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5788669586181641},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5439921617507935},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5150746703147888},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.469757080078125},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4372773766517639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41609466075897217},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41104555130004883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3128548860549927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28904157876968384},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G982102590","display_name":null,"funder_award_id":"92270201,62006151,62076161,62106213,72150002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W107583932","https://openalex.org/W2027595342","https://openalex.org/W2075268401","https://openalex.org/W2091565802","https://openalex.org/W2473418344","https://openalex.org/W2560674852","https://openalex.org/W2594311007","https://openalex.org/W2963470657","https://openalex.org/W2964123095","https://openalex.org/W3011766119","https://openalex.org/W4281900906","https://openalex.org/W6657138077","https://openalex.org/W6824583106"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2970364557","https://openalex.org/W2145363145","https://openalex.org/W2900759811","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276"],"abstract_inverted_index":{"Temporal":[0],"difference":[1],"(TD)":[2],"learning":[3,10,89,128],"with":[4,160,170],"nonlinear":[5,64,87],"function":[6],"approximation":[7],"(nonlinear":[8],"TD":[9,65,88],"for":[11],"short)":[12],"permits":[13],"evaluating":[14],"policies":[15],"using":[16,127,157],"neural":[17],"networks,":[18],"and":[19,112,148,184],"is":[20,84,90,180,186],"a":[21,120,142],"core":[22],"component":[23],"in":[24,52,60,67,93,197],"modern":[25],"deep":[26],"reinforcement":[27],"learning.":[28],"Though":[29],"significant":[30],"advances":[31],"have":[32],"been":[33,42],"made":[34],"to":[35,44,100,134],"improve":[36],"its":[37,73],"effectiveness,":[38],"little":[39],"attention":[40],"has":[41],"paid":[43],"the":[45,57,76,94,131,146,171,181,187,191,201],"data":[46],"privacy":[47,58,74,80,108,137,147],"faced":[48],"when":[49],"applying":[50],"it":[51],"real":[53],"applications.":[54],"To":[55,115],"mitigate":[56],"concerns":[59],"practical":[61],"applications":[62],"of":[63,78,96,130,190,203],"learning,":[66],"this":[68,116],"paper,":[69],"we":[70,118,140],"consider":[71],"preserving":[72,107],"under":[75],"notion":[77],"differential":[79],"(DP).":[81],"This":[82],"problem":[83],"challenging":[85],"since":[86],"usually":[91],"studied":[92],"formulation":[95],"stochastic":[97],"nonconvex-strongly-concave":[98],"optimization":[99],"obtain":[101],"finite-sample":[102],"analysis,":[103],"which":[104,123],"requires":[105],"simultaneously":[106],"on":[109,154],"both":[110,125,155],"primal":[111],"dual":[113],"sides.":[114],"end,":[117],"adopt":[119],"single-timescale":[121],"algorithm,":[122],"optimizes":[124],"sides":[126,156],"rates":[129],"same":[132],"order,":[133],"avoid":[135],"unnecessary":[136],"costs.":[138],"Further,":[139],"achieve":[141],"good":[143],"trade-off":[144],"between":[145],"utility":[149,172],"guarantees":[150],"by":[151,175],"perturbing":[152],"gradients":[153],"Gaussian":[158],"noises":[159],"well-calibrated":[161],"variances.":[162],"Consequently,":[163],"our":[164,204],"algorithm":[165],"achieves":[166],"rigorous":[167],"(\u03b5,\u03b4)-DP":[168],"guarantee":[169],"upper":[173],"bounded":[174],"~O((d/log(1/\u03b4))1/8":[176],"(n\u03b5)1/4)":[177],"where":[178],"n":[179],"trajectory":[182],"length":[183],"d":[185],"ambient":[188],"dimension":[189],"feature":[192],"space.":[193],"Extensive":[194],"experiments":[195],"conducted":[196],"OpenAI":[198],"Gym":[199],"validate":[200],"advantages":[202],"algorithm.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}