The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Local Privacy and Statistical Minimax Rates
Abstract
Working under local differential privacy-a model of privacy in which data remains private even from the statistician or learner-we study the tradeoff between privacy guarantees and the utility of the resulting statistical estimators. We prove bounds on information-theoretic quantities, including mutual information and Kullback-Leibler divergence, that influence estimation rates as a function of the amount of privacy preserved. When combined with minimax techniques such as Le Cam's and Fano's methods, these inequalities allow for a precise characterization of statistical rates under local privacy constraints. In this paper, we provide a treatment of two canonical problem families: mean estimation in location family models and convex risk minimization. For these families, we provide lower and upper bounds for estimation of population quantities that match up to constant factors, giving privacy-preserving mechanisms and computationally efficient estimators that achieve the bounds.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Elements of Information Theory
Cover, T. M., & Thomas, J. A. (2005) · doi:10.1002/047174882x · Cited by 13,791
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Research works printed but not linked: 25
- 10.1145/293347.293351 · DOI · Paper page
- 10.1145/1806689.1806786 · DOI · Paper page
- 10.1137/090756090 · DOI · Paper page
- hall, 2011, Random Differential Privacy
- 10.1109/FOCS.2010.85 · DOI · Paper page
- 10.1145/773153.773174 · DOI · Paper page
- fienberg, 2010, Differential privacy and the risk-utility tradeoff for multidimensional contingency tables, The International Conference on Privacy in Statistical Databases, 10.1007/978-3-642-15838-4_17 · DOI
- 10.1109/FOCS.2010.12 · DOI · Paper page
- nemirovski, 1983, Problem Complexity and Method Efficiency in Optimization
- 10.1109/FOCS.2010.14 · DOI
- 10.1145/1993636.1993743 · DOI
- tsybakov, 2009, Introduction to Nonparametric Estimation, 10.1007/b13794 · DOI · Paper page
- 10.1214/aoms/1177732144 · DOI · Paper page
- 10.1080/01621459.1965.10480775 · DOI · Paper page
- 10.1198/jasa.2009.tm08651 · DOI · Paper page
- yang, 1999, Information-theoretic determination of minimax rates of convergence, Annals of Statistics, 27, 1564, 10.1214/aos/1017939142 · DOI · Paper page
- assouad, 1997, Festschrift for Lucien Le Cam, 423
- beimel, 2008, Distributed private data analysis: Simultaneously solving how and what, Advances in Cryptology, 451
- 10.1145/1265530.1265569 · DOI · Paper page
- 10.1145/1536414.1536466 · DOI · Paper page
- 10.1109/TIT.2011.2182178 · DOI
- duchi, 2012, Privacy aware learning, Advances in neural information processing systems, 25
- 10.1007/978-3-642-28914-9_18 · DOI
- chaudhuri, 2012, Convergence rates for differentially private statistical estimation, Proceedings of the 29th International Conference on Machine Learning
- 10.1080/01621459.1986.10478229 · DOI
Cited by
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
“While LDP protocols are effective at enforcing privacy and have theoretical justifications [156, 135, 136], a number of results have shown that achieving local differential privacy while preserving utility is challenging particularly, especially in high-dimensional data settings [229, 388, 219, 51, 220, 424, 142, 111].”
BackgroundPractical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956
Mironov, I. (2017) · 2017 IEEE 30th Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2017.11 · Cited by 1,255
Privacy and Robustness in Federated Learning: Attacks and Defenses
Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., & Yu, P. S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216981 · Cited by 548
Differential Privacy for Deep and Federated Learning: A Survey
Ouadrhiri, A. E., & Abdelhadi, A. (2022) · IEEE Access · doi:10.1109/access.2022.3151670 · Cited by 445
Metadata
- Authors
- Duchi, J. C., Jordan, M. I., & Wainwright, M. J.
- Venue
- 2013 IEEE 54th Annual Symposium on Foundations of Computer Science
- Publisher
- IEEE
- Published
- 2013-10
- Pages
- 429-438
- ISSN
- 0272-5428 (ISSN-L)
- OpenAlex
- W2053801139
- Cited by
- 954
- References
- 2
- FWCI
- 17.35
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
