A novel adaptive differential privacy algorithm for empirical risk minimization

DOI10.1142/S021759592140011XMaRDI QIDQ5024903zbMATH OpenOpenAlexFDO

Authors Kaili Zhang, Hai-Bin Zhang, Pengfei Zhao, Haibin Chen

Publication date 1 February 2022

Published in Asia-Pacific Journal of Operational Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/s021759592140011x

zbMATH Keywords

differential privacyempirical risk minimizationiteration algorithm

Mathematics Subject Classification ID

Management decision making, including multiple objectives (90B50) Risk models (general) (91B05)

Recommendations

• Differentially private empirical risk minimization
• The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy
• Differential privacy partitioning algorithm based on adaptive density grids
• The algorithmic foundations of differential privacy
• Differentially private precision matrix estimation

Cites work

• A Stochastic Approximation Method
• Bounds on the sample complexity for private learning and private data release
• Concentrated differential privacy: simplifications, extensions, and lower bounds
• Convex Analysis
• Differentially private empirical risk minimization
• The Composition Theorem for Differential Privacy
• The algorithmic foundations of differential privacy
• The complexity of computing the optimal composition of differential privacy
• Theory of Cryptography

Cited in

(10)

• Empirical risk minimization in the non-interactive local model of differential privacy
• Framework of model fitting under PSO-guided differential privacy
• scientific article; zbMATH DE number 6860834 (Why is no real title available?)
• Differentially private empirical risk minimization
• Distributed Empirical Risk Minimization With Differential Privacy
• Privacy-preserving and lossless distributed estimation of high-dimensional generalized additive mixed models
• Preserving differential privacy in deep neural networks with relevance-based adaptive noise imposition
• Perturbation of convex risk minimization and its application in differential private learning algorithms
• Mitigating disparate impact on model accuracy in differentially private learning
• Model averaging with privacy-preserving

Describes a project that uses

Uses Software

• LIBSVM
• UCI

This page was built for publication: A novel adaptive differential privacy algorithm for empirical risk minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5024903)