A Bias-Accuracy-Privacy Trilemma for Statistical Estimation

DOI10.1080/01621459.2024.2443275MaRDI QIDQ6878067zbMATH OpenFDO

Authors Gautam Kamath, Vikrant Singhal, Thomas Steinke, Jonathan Ullman

Publication date 7 January 2026

Published in Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/01621459.2024.2443275

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• Breakthroughs in statistics. Volume I: Foundations and basic theory
• Collusion-secure fingerprinting for digital data
• Concentrated differential privacy: simplifications, extensions, and lower bounds
• Efficient mean estimation with pure differential privacy via a sum-of-squares exponential mechanism
• Fingerprinting codes and the price of approximate differential privacy
• Local privacy and statistical minimax rates
• Make Up Your Mind: The Price of Online Queries in Differential Privacy
• Mathematical methods of statistics.
• Max-information, differential privacy, and post-selection hypothesis testing
• On the sample complexity of privately learning unbounded high-dimensional Gaussians
• Optimal probabilistic fingerprint codes
• Preventing false discovery in interactive data analysis is hard
• Robust traceability from trace amounts
• The complexity of differential privacy
• The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy
• The reusable holdout: preserving validity in adaptive data analysis
• Theory of Cryptography
• Tight lower bounds for differentially private selection

This page was built for publication: A Bias-Accuracy-Privacy Trilemma for Statistical Estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6878067)