Learning privately with labeled and unlabeled examples

DOI10.1007/s00453-020-00753-zOpenAlexW3067150248MaRDI QIDQ2223696

Amos Beimel, Kobbi Nissim, Uri Stemmer

Publication date: 1 February 2021

Published in: Algorithmica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1407.2662

zbMATH Keywords

PAC learningactive learningdifferential privacysemi-supervised learning

Mathematics Subject Classification ID

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

Uses Software

• SuLQ

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A general lower bound on the number of examples needed for learning
• Bounds on the sample complexity for private learning and private data release
• On the density of families of sets
• Simultaneous Private Learning of Multiple Concepts
• Privately Releasing Conjunctions and the Statistical Query Barrier
• Preserving Statistical Validity in Adaptive Data Analysis
• Characterizing the sample complexity of private learners
• What Can We Learn Privately?
• Efficient noise-tolerant learning from statistical queries
• Sample Complexity Bounds on Differentially Private Learning via Communication Complexity
• Learnability and the Vapnik-Chervonenkis dimension
• Our Data, Ourselves: Privacy Via Distributed Noise Generation
• A theory of the learnable
• Private stochastic convex optimization: optimal rates in linear time
• Private PAC learning implies finite Littlestone dimension
• Fingerprinting codes and the price of approximate differential privacy
• Probability of error of some adaptive pattern-recognition machines
• Algorithmic stability for adaptive data analysis
• A learning theory approach to noninteractive database privacy
• Learning with a probabilistic teacher
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Theory of Cryptography

This page was built for publication: Learning privately with labeled and unlabeled examples