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

DOI10.1186/s13660-016-1280-0zbMath1359.90096WikidataQ37562838 ScholiaQ37562838MaRDI QIDQ504548

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

perturbation; concentration inequality; differential privacy; error decomposition; convex risk minimization

Mathematics Subject Classification ID

90C25: Convex programming

Related Items

\(\mathcal {JHR}\)-operator pairs in \(C^{*}\)-algebra-valued modular metric spaces and related fixed point results via \(C_{*}\)-class functions

Uses Software

• PrivateLR

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation analysis of learning algorithms for support vector regression and quantile regression
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Estimating conditional quantiles with the help of the pinball loss
• Learning theory estimates for coefficient-based regularized regression
• Conditional quantiles with varying Gaussians
• Learning with sample dependent hypothesis spaces
• Learning theory estimates via integral operators and their approximations
• On the mathematical foundations of learning
• Preserving Statistical Validity in Adaptive Data Analysis
• Learning Theory
• Differential Privacy: A Survey of Results
• 10.1162/153244302760200704
• Probability Inequalities for Sums of Bounded Random Variables
• Algorithmic stability for adaptive data analysis
• Theory of Cryptography
• Differential Privacy