{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:13:48Z","timestamp":1758892428639,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1716400","IIS-1919492"],"award-info":[{"award-number":["CCF-1716400","IIS-1919492"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tit.2020.3040406","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T21:55:15Z","timestamp":1606341315000},"page":"1182-1200","source":"Crossref","is-referenced-by-count":14,"title":["On Sparse Linear Regression in the Local Differential Privacy Model"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4908-0243","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5730-9429","authenticated-orcid":false,"given":"Jinhui","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Differentially private empirical risk minimization: Efficient algorithms and tight error bounds","author":"bassily","year":"2014","journal-title":"arXiv 1405 7085"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2019.00015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/665"},{"key":"ref32","first-page":"685","article-title":"On iterative hard thresholding methods for high-dimensional m-estimation","author":"jain","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"2719","article-title":"Differentially private empirical risk minimization revisited: Faster and more general","author":"wang","year":"2017","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011182"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/15M1033587"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2165799"},{"key":"ref35","article-title":"Inference under information constraints I: Lower bounds from chi-square contraction","author":"acharya","year":"2018","journal-title":"arXiv 1812 11476"},{"key":"ref34","article-title":"Differentially private Assouad, Fano, and Le Cam","author":"acharya","year":"2020","journal-title":"arXiv 2004 06830"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5411"},{"key":"ref27","first-page":"973","article-title":"Empirical risk minimization in non-interactive local differential privacy revisited","author":"wang","year":"2018","journal-title":"Proc Annu Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref29","first-page":"897","article-title":"Noninteractive locally private learning of linear models via polynomial approximations","author":"wang","year":"2019","journal-title":"Proc Algorithmic Learn Theory"},{"journal-title":"Statistical Methods for the Social and Behavioral Sciences","year":"1988","author":"marascuilo","key":"ref2"},{"key":"ref1","first-page":"6628","article-title":"On sparse linear regression in the local differential privacy model","volume":"97","author":"wang","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref20","first-page":"1","article-title":"Private convex empirical risk minimization and high-dimensional regression","author":"kifer","year":"2012","journal-title":"Proc Conf Learn Theory"},{"key":"ref22","first-page":"819","article-title":"Differentially private feature selection via stability arguments, and the robustness of the lasso","author":"thakurta","year":"2013","journal-title":"Proc Conf Learn Theory"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.35"},{"key":"ref24","first-page":"523","article-title":"Differentially private Bayesian linear regression","author":"bernstein","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"3025","article-title":"Nearly optimal private lasso","author":"talwar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"4130","article-title":"Collect at once, use effectively: Making non-interactive locally private learning possible","author":"zheng","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","article-title":"The cost of privacy: Optimal rates of convergence for parameter estimation with differential privacy","author":"tony cai","year":"2019","journal-title":"arXiv 1902 04495"},{"key":"ref50","article-title":"Private empirical risk minimization beyond the worst case: The effect of the constraint set geometry","author":"talwar","year":"2014","journal-title":"arXiv 1411 5417"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1015957395"},{"key":"ref53","article-title":"Introduction to the non-asymptotic analysis of random matrices","author":"vershynin","year":"2010","journal-title":"arXiv 1011 3027"},{"journal-title":"UCI Machine Learning Repository","year":"2017","author":"dheeru","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1389735"},{"key":"ref11","article-title":"The right complexity measure in locally private estimation: It is not the Fisher information","author":"duchi","year":"2018","journal-title":"arXiv 1806 05756"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3196959.3196981"},{"key":"ref12","first-page":"258","article-title":"Nonlinear structured signal estimation in high dimensions via iterative hard thresholding","author":"zhang","year":"2018","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref13","first-page":"2472","article-title":"Sparse nonlinear regression: Parameter estimation under nonconvexity","author":"yang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"155","article-title":"Sample complexity bounds for differentially private learning","author":"chaudhuri","year":"2011","journal-title":"Proc 24th Annu Conf Learn Theory"},{"key":"ref15","first-page":"363","article-title":"Private learning and sanitization: Pure vs. approximate differential privacy","author":"beimel","year":"2013","journal-title":"APPROX"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2018.1538881"},{"key":"ref18","first-page":"93","article-title":"Revisiting differentially private linear regression: Optimal and adaptive prediction & estimation in unbounded domain","author":"wang","year":"2018","journal-title":"Proc Conf Uncertainty in Artif Intell (UAI)"},{"key":"ref19","first-page":"3105","article-title":"Differentially private ordinary least squares","volume":"70","author":"sheffet","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-20192-9","author":"b\u00fchlmann","year":"2011","journal-title":"Statistics for high-dimensional data methods theory and applications"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0056976","article-title":"Linear regression in genetic association studies","volume":"8","author":"bu\u017ekov\u00e1","year":"2013","journal-title":"PLoS ONE"},{"key":"ref6","article-title":"Differential privacy at scale: Uber and Berkeley collaboration","author":"near","year":"2018","journal-title":"Proc Enigma (Enigma)"},{"key":"ref5","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","author":"dwork","year":"2006","journal-title":"Proc Theory Cryptogr Conf"},{"key":"ref8","article-title":"Privacy loss in apple’s implementation of differential privacy on MacOS 10.12","author":"tang","year":"2017","journal-title":"arXiv 1709 02753"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660348"},{"key":"ref49","first-page":"807","article-title":"Greedy sparsity-constrained optimization","volume":"14","author":"bahmani","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"429","article-title":"Local privacy and statistical minimax rates","author":"duchi","year":"2013","journal-title":"Proc Annu IEEE Symp Foundations Comput Sci"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362257"},{"key":"ref45","first-page":"1589","article-title":"Minimax-optimal privacy-preserving sparse PCA in distributed systems","author":"ge","year":"2018","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1214\/12-STS400"},{"key":"ref42","first-page":"635","article-title":"Concentrated differential privacy: Simplifications, extensions, and lower bounds","author":"bun","year":"2016","journal-title":"Proc Theory Cryptogr Conf"},{"key":"ref41","first-page":"263","article-title":"Rényi differential privacy","author":"mironov","year":"2017","journal-title":"Proc IEEE 30th Comput Secur Found Symp (CSF)"},{"key":"ref44","first-page":"1","article-title":"Compressive sensing and structured random matrices","volume":"9","author":"rauhut","year":"2010","journal-title":"Theoretical Foundations and Numerical Methods for Sparse Recovery"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2009.04.002"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/9333790\/9269994-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/9333790\/09269994.pdf?arnumber=9269994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:16Z","timestamp":1652194456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9269994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":55,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tit.2020.3040406","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"type":"print","value":"0018-9448"},{"type":"electronic","value":"1557-9654"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}