Private least absolute deviations with heavy-tailed data

DOI10.1016/J.TCS.2025.115071MaRDI QIDQ7028333zbMATH OpenFDO

Authors Di Wang, Jinhui Xu

Publication date 12 February 2025

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.TCS.2025.115071

zbMATH Keywords

differential privacyregressionrobust estimation

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Privacy of data (68P27) Stochastic programming (90C15) Convex programming (90C25) Applications of mathematical programming (90C90)

Cites work

• A generalized Catoni's M-estimator under finite \(\alpha\)-th moment assumption with \(\alpha \in (1,2)\)
• High-dimensional probability. An introduction with applications in data science
• Private empirical risk minimization: efficient algorithms and tight error bounds
• Private stochastic convex optimization: optimal rates in linear time
• Private stochastic optimization with large worst-case Lipschitz parameter: optimal rates for (non-smooth) convex losses and extension to non-convex losses
• The algorithmic foundations of differential privacy
• The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy
• Theory of Cryptography

This page was built for publication: Private least absolute deviations with heavy-tailed data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7028333)