Document Open Access Logo

Differentially Private Medians and Interior Points for Non-Pathological Data

Authors Maryam Aliakbarpour, Rose Silver, Thomas Steinke, Jonathan Ullman

PDF
Thumbnail PDF

File

LIPIcs.ITCS.2024.3.pdf
  • Filesize: 0.82 MB
  • 21 pages

Document Identifiers

Author Details

Maryam Aliakbarpour
  • Department of Computer Science, Rice University, Houston, TX, USA
Rose Silver
  • Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA
Thomas Steinke
  • Google DeepMind, Mountain View, CA, USA
Jonathan Ullman
  • Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA

Funding

  • Aliakbarpour, Maryam: Supported by NSF grants CNS-2120667, CNS-2120603, CCF-1934846, and BU’s Hariri Institute for Computing. This work was predominantly done while she was affiliated with Boston University and Northeastern University.
  • Silver, Rose: Supported by NSF CCF-1750640 and CNS-2120603.
  • Ullman, Jonathan: Supported by NSF CCF-1750640 and CNS-2120603.

Cite AsGet BibTex

Maryam Aliakbarpour, Rose Silver, Thomas Steinke, and Jonathan Ullman. Differentially Private Medians and Interior Points for Non-Pathological Data. In 15th Innovations in Theoretical Computer Science Conference (ITCS 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 287, pp. 3:1-3:21, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
https://doi.org/10.4230/LIPIcs.ITCS.2024.3

Abstract

We construct sample-efficient differentially private estimators for the approximate-median and interior-point problems, that can be applied to arbitrary input distributions over ℝ satisfying very mild statistical assumptions. Our results stand in contrast to the surprising negative result of Bun et al. (FOCS 2015), which showed that private estimators with finite sample complexity cannot produce interior points on arbitrary distributions.

Subject Classification

ACM Subject Classification
  • Theory of computation → Theory of database privacy and security
Keywords
  • Differential Privacy
  • Statistical Estimation
  • Approximate Medians
  • Interior Point Problem

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Related Versions

References

  1. Maryam Aliakbarpour, Rose Silver, Thomas Steinke, and Jonathan Ullman. Differentially private medians and interior points for non-pathological data. arXiv preprint, 2023. URL: https://arxiv.org/abs/2305.13440.
  2. Noga Alon, Roi Livni, Maryanthe Malliaris, and Shay Moran. Private pac learning implies finite littlestone dimension. In Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, pages 852-860, 2019. URL: https://arxiv.org/abs/1806.00949.
  3. Hilal Asi and John C Duchi. Near instance-optimality in differential privacy. arXiv preprint, 2020. URL: https://arxiv.org/abs/2005.10630.
  4. Amos Beimel, Shay Moran, Kobbi Nissim, and Uri Stemmer. Private center points and learning of halfspaces. In Conference on Learning Theory, pages 269-282. PMLR, 2019. Google Scholar
  5. Amos Beimel, Kobbi Nissim, and Uri Stemmer. Private learning and sanitization: Pure vs. approximate differential privacy. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques, RANDOM-APPROX '13, pages 363-378. Springer, 2013. Google Scholar
  6. Daniel Berend and Aryeh Kontorovich. A sharp estimate of the binomial mean absolute deviation with applications. Statistics & Probability Letters, 83(4):1254-1259, 2013. URL: https://doi.org/10.1016/j.spl.2013.01.023.
  7. Victor-Emmanuel Brunel and Marco Avella-Medina. Propose, test, release: Differentially private estimation with high probability. arXiv preprint, 2020. URL: https://arxiv.org/abs/2002.08774.
  8. Mark Bun, Cynthia Dwork, Guy N Rothblum, and Thomas Steinke. Composable and versatile privacy via truncated cdp. In Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing, pages 74-86, 2018. Google Scholar
  9. Mark Bun, Kobbi Nissim, Uri Stemmer, and Salil Vadhan. Differentially private release and learning of threshold functions. In IEEE 56th Annual Symposium on Foundations of Computer Science (FOCS), pages 634-649, 2015. Google Scholar
  10. Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, and Uri Stemmer. Optimal differentially private learning of thresholds and quasi-concave optimization. In Proceedings of the 55th Annual ACM Symposium on Theory of Computing, pages 472-482, 2023. Google Scholar
  11. Edwin L. Crow. The mean deviation of the poisson distribution. Biometrika, 45(3/4):556-559, 1958. URL: http://www.jstor.org/stable/2333201.
  12. Cynthia Dwork and Jing Lei. Differential privacy and robust statistics. In Proceedings of the 41st ACM Symposium on Theory of Computing, STOC '09, pages 371-380. ACM, 2009. Google Scholar
  13. Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. Calibrating noise to sensitivity in private data analysis. In Conference on Theory of Cryptography, TCC '06, pages 265-284, New York, NY, USA, 2006. Google Scholar
  14. Nika Haghtalab, Tim Roughgarden, and Abhishek Shetty. Smoothed analysis of online and differentially private learning. Advances in Neural Information Processing Systems, 33:9203-9215, 2020. Google Scholar
  15. Haim Kaplan, Katrina Ligett, Yishay Mansour, Moni Naor, and Uri Stemmer. Privately learning thresholds: Closing the exponential gap. In Conference on Learning Theory, pages 2263-2285. PMLR, 2020. Google Scholar
  16. Vishesh Karwa and Salil Vadhan. Finite sample differentially private confidence intervals. In 9th Innovations in Theoretical Computer Science Conference (ITCS 2018). Schloss Dagstuhl-Leibniz - Zentrum für Informatik, 2018. URL: https://arxiv.org/abs/1711.03908.
  17. Adam Smith and Jonathan Ullman. Privacy in statistics and machine learning spring 2021 lecture 9: Approximate differential privacy. URL: https://dpcourse.github.io/2021-spring/index.html.
  18. Christos Tzamos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, and Ilias Zadik. Optimal private median estimation under minimal distributional assumptions. Advances in Neural Information Processing Systems, 33:3301-3311, 2020. Google Scholar
  19. Salil Vadhan. The complexity of differential privacy, 2016. URL: https://privacytools.seas.harvard.edu/files/privacytools/files/complexityprivacy_1.pdf.
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact