{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:56:08Z","timestamp":1774540568080,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CIF 1900750,CIF CAREER 1845852,CCF 0939370"],"award-info":[{"award-number":["CIF 1900750,CIF CAREER 1845852,CCF 0939370"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,12]]},"DOI":"10.1109\/isit45174.2021.9518124","type":"proceedings-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T16:52:42Z","timestamp":1630515162000},"page":"344-349","source":"Crossref","is-referenced-by-count":15,"title":["Differentially Private Federated Learning: An Information-Theoretic Perspective"],"prefix":"10.1109","author":[{"given":"Shahab","family":"Asoodeh","sequence":"first","affiliation":[{"name":"Harvard University"}]},{"given":"Wei-Ning","family":"Chen","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Flavio P.","family":"Calmon","sequence":"additional","affiliation":[{"name":"Harvard University"}]},{"given":"Ayfer","family":"\u00d6zg\u00fcr","sequence":"additional","affiliation":[{"name":"Stanford University"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref38","article-title":"Making gradient descent optimal for strongly convex stochastic optimization","author":"rakhlin","year":"2011","journal-title":"ArXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-7005-6_6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/1101006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176995937"},{"key":"ref30","first-page":"638","volume":"11693","author":"balle","year":"2019","journal-title":"The privacy blanket of the shuffle model"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988614"},{"key":"ref36","author":"asoodeh","year":"2021","journal-title":"Differentially private federated learning An information-theoretic perspective"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2015.7282881"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2482978"},{"key":"ref10","first-page":"819","article-title":"Differentially private feature selection via stability arguments, and the robustness of the lasso","volume":"30","author":"thakurta","year":"2013","journal-title":"Proc Conf Learning Theory"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2013.6736861"},{"key":"ref12","first-page":"476","article-title":"(near) dimension independent risk bounds for differentially private learning","volume":"32","author":"jain","year":"2014","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.35"},{"key":"ref14","first-page":"27192728","article-title":"Differentially private empirical risk minimization revisited: Faster and more general","author":"wang","year":"0","journal-title":"Proc Neural Inf Proc Systems"},{"key":"ref15","article-title":"Generative models for effective ml on private, decentralized datasets","author":"augenstein","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2018.00056"},{"key":"ref17","first-page":"13277","article-title":"Privacy amplification by mixing and diffusion mechanisms","author":"balle","year":"0","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref19","article-title":"Privacy analysis of online learning algorithms via contraction coefficients","author":"asoodeh","year":"2020","journal-title":"ArXiv"},{"key":"ref28","first-page":"6280","article-title":"Privacy amplification by subsampling: Tight analyses via couplings and divergences","author":"balle","year":"0","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064047"},{"key":"ref27","first-page":"1226","article-title":"Subsampled Rényi differential privacy and analytical moments accountant","volume":"89","author":"wang","year":"2018","journal-title":"AISTAT"},{"key":"ref3","article-title":"Inference attacks against collaborative learning","volume":"abs 1805 4049","author":"melis","year":"2018","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/11818175_12"},{"key":"ref29","article-title":"Hypothesis testing interpretations and Rényi differential privacy","author":"balle","year":"0","journal-title":"AISTAT"},{"key":"ref5","first-page":"1069","article-title":"Differentially private empirical risk minimization","volume":"12","author":"chaudhuri","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"11282","article-title":"Private stochastic convex optimization with optimal rates","author":"bassily","year":"0","journal-title":"Neural Inf Proc Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref9","first-page":"24.1","article-title":"Differentially private online learning","volume":"23","author":"jain","year":"2012","journal-title":"Proc Conf Learning Theory"},{"key":"ref1","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"0","journal-title":"AISTATS"},{"key":"ref20","first-page":"46","article-title":"Without-replacement sampling for stochastic gradient methods","volume":"29","author":"shamir","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1966.tb00626.x"},{"key":"ref21","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","author":"dwork","year":"0","journal-title":"Proceedings of Theoretical Cryptography Conference (TCC)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.110.080501"},{"key":"ref23","first-page":"299","article-title":"Information-type measures of difference of probability distributions and indirect observations","volume":"2","author":"csisz\u00e1r","year":"1967","journal-title":"Studia Sci Math Hungar"},{"key":"ref26","first-page":"394","article-title":"Improving the Gaussian mechanism for differential privacy: Analytical calibration and optimal denoising","volume":"80","author":"balle","year":"2018","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39212-2_8"}],"event":{"name":"2021 IEEE International Symposium on Information Theory (ISIT)","location":"Melbourne, Australia","start":{"date-parts":[[2021,7,12]]},"end":{"date-parts":[[2021,7,20]]}},"container-title":["2021 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9517708\/9517709\/09518124.pdf?arnumber=9518124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:36:11Z","timestamp":1773347771000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9518124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,12]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/isit45174.2021.9518124","relation":{},"subject":[],"published":{"date-parts":[[2021,7,12]]}}}