Differentially private distributed logistic regression with the objective function perturbation

DOI10.1142/S0219691322500436MaRDI QIDQ5880591zbMATH OpenFDO

Authors Haibo Yang, Bin Zou, Yingxiong Fu

Publication date 3 March 2023

Published in International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/S0219691322500436

zbMATH Keywords

differentially private distributed learning algorithmsdistributed learninglogistic regressionobjective function perturbation

Mathematics Subject Classification ID

Data structures (68P05) Artificial neural networks and deep learning (68T07) Informational aspects of data analysis and big data (94A16)

Recommendations

• Differentially private empirical risk minimization
• A privacy-masking learning algorithm for online distributed optimization over time-varying unbalanced digraphs
• Distributed online bandit linear regressions with differential privacy
• Differentially private distributed optimization for multi-agent systems via the augmented Lagrangian algorithm
• Perturbation of convex risk minimization and its application in differential private learning algorithms

Cites work

• A learning theory approach to noninteractive database privacy
• Differentially Private Distributed Constrained Optimization
• Differentially private empirical risk minimization
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• First-order methods in optimization
• scientific article; zbMATH DE number 3850830 (Why is no real title available?)
• k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
• The algorithmic foundations of differential privacy

Cited in

(6)

• An optimal (, )-differentially private learning of distributed deep fuzzy models
• Distributionally-robust machine learning using locally differentially-private data
• Perturbation of convex risk minimization and its application in differential private learning algorithms
• Framework of model fitting under PSO-guided differential privacy
• Distributed online bandit linear regressions with differential privacy
• Distributed Empirical Risk Minimization With Differential Privacy

This page was built for publication: Differentially private distributed logistic regression with the objective function perturbation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5880591)