Differentially private regularized stochastic convex optimization with heavy-tailed data

DOI10.5705/SS.202022.0282MaRDI QIDQ7022497zbMATH OpenFDO

Authors Haihan Xie, Matthew Stephen Pietrosanu, Yi Liu, Wei Tu, Bei Jiang, Linglong Kong

Publication date 25 February 2025

Published in Statistica Sinica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.5705/SS.202022.0282

zbMATH Keywords

privacy protectionerror boundnon-smooth regularizationrandomized mechanism

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• A Proximal Gradient Algorithm for Decentralized Composite Optimization
• Balancing Inferential Integrity and Disclosure Risk Via Model Targeted Masking and Multiple Imputation
• Convergence of stochastic proximal gradient algorithm
• Differential Privacy: A Survey of Results
• Differentially private empirical risk minimization
• Empirical risk minimization for heavy-tailed losses
• Gaussian Differential Privacy
• Loss minimization and parameter estimation with heavy tails
• On perturbed proximal gradient algorithms
• Private empirical risk minimization: efficient algorithms and tight error bounds
• Signal Recovery by Proximal Forward-Backward Splitting
• The algorithmic foundations of differential privacy
• Theory of Cryptography

This page was built for publication: Differentially private regularized stochastic convex optimization with heavy-tailed data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7022497)