A learning theory approach to noninteractive database privacy

DOI10.1145/2450142.2450148zbMath1281.68092OpenAlexW2042469398MaRDI QIDQ5395711

Katrina Ligett, Aaron Roth, Avrim L. Blum

Publication date: 17 February 2014

Published in: Journal of the ACM (Search for Journal in Brave)

Full work available at URL: https://resolver.caltech.edu/CaltechAUTHORS:20190114-152232213

zbMATH Keywords

learning theorynoninteractive database privacy

Mathematics Subject Classification ID

Computational learning theory (68Q32) Database theory (68P15)

Related Items

Private Sequential Learning, Differentially private distributed logistic regression with the objective function perturbation, Differentially private data publishing for arbitrarily partitioned data, Sample Complexity Bounds on Differentially Private Learning via Communication Complexity, Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds, Strong Hardness of Privacy from Weak Traitor Tracing, Unnamed Item, Private Sampling: A Noiseless Approach for Generating Differentially Private Synthetic Data, Covariance's loss is privacy's gain: computationally efficient, private and accurate synthetic data, PAC learning halfspaces in non-interactive local differential privacy model with public unlabeled data, Differentially private range query on shortest paths, Differentially private trajectory event streams publishing under data dependence constraints, Comparative study of differentially private data synthesis methods, Learning privately with labeled and unlabeled examples, Differential Privacy on Finite Computers, Bounds on the sample complexity for private learning and private data release, What Can We Learn Privately?, Private Matchings and Allocations, The Complexity of Differential Privacy