Perturbation of convex risk minimization and its application in differential private learning algorithms

DOI10.1186/S13660-016-1280-0MaRDI QIDQ504548zbMATHOpenAlexWikidataFDO

Authors Weilin Nie, Cheng Wang

Publication date 17 January 2017

Published in Journal of Inequalities and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1186/s13660-016-1280-0

zbMATH Keywords

concentration inequalityperturbationdifferential privacyerror decompositionconvex risk minimization

Mathematics Subject Classification ID

Convex programming (90C25)

Recommendations

• Differentially private empirical risk minimization
• Differentially private distributed logistic regression with the objective function perturbation
• Differentially private SGD with non-smooth losses
• Privacy aware learning
• A novel adaptive differential privacy algorithm for empirical risk minimization

Cites work

• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• 10.1162/153244302760200704
• Algorithmic stability for adaptive data analysis
• Approximation analysis of learning algorithms for support vector regression and quantile regression
• Conditional quantiles with varying Gaussians
• Differential Privacy
• Differential Privacy: A Survey of Results
• Differentially private empirical risk minimization
• Estimating conditional quantiles with the help of the pinball loss
• Learnability, stability and uniform convergence
• Learning Theory
• Learning theory estimates for coefficient-based regularized regression
• Learning theory estimates via integral operators and their approximations
• Learning with differential privacy: stability, learnability and the sufficiency and necessity of ERM principle
• Learning with sample dependent hypothesis spaces
• On the mathematical foundations of learning
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Preserving statistical validity in adaptive data analysis (extended abstract)
• Probability Inequalities for Sums of Bounded Random Variables
• Support vector machine soft margin classifiers: error analysis
• Theory of Cryptography

Cited in

(3)

• Differentially private SGD with non-smooth losses
• Differentially private distributed logistic regression with the objective function perturbation
• \(\mathcal {JHR}\)-operator pairs in \(C^{*}\)-algebra-valued modular metric spaces and related fixed point results via \(C_{*}\)-class functions

Describes a project that uses

Uses Software

• PrivateLR

This page was built for publication: Perturbation of convex risk minimization and its application in differential private learning algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q504548)