Differentially private release and learning of threshold functions

DOI10.1109/FOCS.2015.45MaRDI QIDQ6946867zbMATH OpenFDO

Authors Uri Stemmer, Mark Bun, Salil Vadhan, Kobbi Nissim

Publication date 5 August 2025

Full work available at URL https://doi.org/10.1109/FOCS.2015.45

Mathematics Subject Classification ID

Theory of computing (68Qxx) Discrete mathematics in relation to computer science (68Rxx) Algorithms in computer science (68Wxx)

Cited in

(12)

• Differentially private medians and interior points for non-pathological data
• Differentially private sampling from distributions
• A polynomial time, pure differentially private estimator for binary product distributions
• Not all learnable distribution classes are privately learnable
• Private PAC learning may be harder than online learning
• Mixtures of Gaussians are privately learnable with a polynomial number of samples
• Privately answering classification queries in the agnostic PAC model
• Sampling without compromising accuracy in adaptive data analysis
• Differentially private Assouad, Fano, and Le Cam
• Approximate range counting under differential privacy
• Securing dynamic data: a primer on differentially private data structures (invited talk)
• Solving linear programs with differential privacy

This page was built for publication: Differentially private release and learning of threshold functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6946867)