Sampling without compromising accuracy in adaptive data analysis

MaRDI QIDQ7025140zbMATH OpenFDO

Authors Benjamin Fish, Lev Reyzin, Benjamin I. P. Rubinstein

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/fish20a.html

zbMATH Keywords

adaptive data analysisdifferential privacysublinear-time algorithms

Mathematics Subject Classification ID

Privacy of data (68P27) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Algorithmic stability for adaptive data analysis
• An Efficient Method for Weighted Sampling without Replacement
• Boosting and differential privacy
• Differentially private release and learning of threshold functions
• Efficient noise-tolerant learning from statistical queries
• Exact post-selection inference, with application to the Lasso
• Faster methods for random sampling
• Fingerprinting codes and the price of approximate differential privacy
• scientific article; zbMATH DE number 2080649 (Why is no real title available?)
• scientific article; zbMATH DE number 5485574 (Why is no real title available?)
• Max-information, differential privacy, and post-selection hypothesis testing
• Preserving statistical validity in adaptive data analysis (extended abstract)
• Private empirical risk minimization: efficient algorithms and tight error bounds
• Statistical algorithms and a lower bound for detecting planted cliques
• Statistical query algorithms for mean vector estimation and stochastic convex optimization
• The algorithmic foundations of differential privacy
• Theory of Cryptography
• Weakly learning DNF and characterizing statistical query learning using Fourier analysis

Cited in

(1)

• Subsampling suffices for adaptive data analysis

This page was built for publication: Sampling without compromising accuracy in adaptive data analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025140)