Minimax Optimal Procedures for Locally Private Estimation
366
TL;DR: In this paper, the tradeoff between privacy guarantees and the risk of the resulting statistical estimators is studied under a model of privacy in which data remain private even from the statistician.
read more
Abstract: Working under a model of privacy in which data remain private even from the statistician, we study the tradeoff between privacy guarantees and the risk of the resulting statistical estimators. We develop private versions of classical information-theoretical bounds, in particular those due to Le Cam, Fano, and Assouad. These inequalities allow for a precise characterization of statistical rates under local privacy constraints and the development of provably (minimax) optimal estimation procedures. We provide a treatment of several canonical families of problems: mean estimation and median estimation, generalized linear models, and nonparametric density estimation. For all of these families, we provide lower and upper bounds that match up to constant factors, and exhibit new (optimal) privacy-preserving mechanisms and computationally efficient estimators that achieve the bounds. Additionally, we present a variety of experimental results for estimation problems involving sensitive data, including sal...
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Mobile Data Collection and Analysis with Local Differential Privacy
Ninghui Li,Qingqing Ye +1 more
- 10 Jun 2019
TL;DR: This seminar talk first introduces the rationale of LDP model behind deployed systems to collect and analyze usage data privately, then surveys the current research landscape in LDP, and identifies several open problems and research directions in this community.
16
•Posted Content
Collecting and Analyzing Multidimensional Data with Local Differential Privacy
TL;DR: Li et al. as discussed by the authors proposed novel LDP mechanisms for collecting a numeric attribute, whose accuracy is at least no worse (and usually better) than existing solutions in terms of worst-case noise variance.
16
SignDS-FL: Local Differentially Private Federated Learning with Sign-based Dimension Selection
TL;DR: An improved framework is proposed, SignDS-FL, which shares the concept of dimension selection with Reference, but saves the privacy cost for the value perturbation stage by assigning random sign values to the selected dimensions and an Exponential Mechanism-based Multi-Dimension Selection algorithm that further improves model convergence and accuracy.
16
•Posted Content
Interactive versus non-interactive locally differentially private estimation: Two elbows for the quadratic functional
TL;DR: It is shown that for estimating the integrated square of a density, sequentially interactive procedures improve substantially over the best possible non-interactive procedure in terms of minimax rate of estimation.
16
OpBoost
TL;DR: In this paper , Xu et al. proposed three order-preserving desensitization algorithms satisfying a variant of Local Differential Privacy (LDP), called distance-based LDP (dLDP), to improve the accuracy of tree boosting algorithms satisfying differential privacy under vertical FL.
15
References
Advances in Neural Information Processing Systems 28
Peter A. Flach,Meelis Kull +1 more
- 12 Dec 2015
13.6K
Calibrating noise to sensitivity in private data analysis
Cynthia Dwork,Frank McSherry,Kobbi Nissim,Adam Smith +3 more
- 04 Mar 2006
TL;DR: In this article, the authors show that for several particular applications substantially less noise is needed than was previously understood to be the case, and also show the separation results showing the increased value of interactive sanitization mechanisms over non-interactive.
•Book
Introduction to Nonparametric Estimation
Alexandre B. Tsybakov
- 22 Oct 2008
TL;DR: The main idea is to introduce the fundamental concepts of the theory while maintaining the exposition suitable for a first approach in the field, and many important and useful results on optimal and adaptive estimation are provided.
Randomized response: a survey technique for eliminating evasive answer bias.
TL;DR: A survey technique for improving the reliability of responses to sensitive interview questions is described, which permits the respondent to answer "yes" or "no" to a question without the interviewer knowing what information is being conveyed by the respondent.
3.4K
Related Papers (5)
Cynthia Dwork,Aaron Roth +1 more
- 11 Aug 2014
John C. Duchi,Michael I. Jordan,Martin J. Wainwright +2 more
- 26 Oct 2013