Bounds on the sample complexity for private learning and private data release

DOI10.1007/s10994-013-5404-1zbMath1311.68131WikidataQ59379624 ScholiaQ59379624MaRDI QIDQ2251471

Kobbi Nissim, Amos Beimel, Shiva Prasad Kasiviswanathan, Hai Brenner

Publication date: 14 July 2014

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-013-5404-1

zbMATH Keywords

PAC learning; differential privacy; sample complexity; private learning; private data release

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Bounds on the Sample Complexity for Private Learning and Private Data Release

Uses Software

• SuLQ

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A general lower bound on the number of examples needed for learning
• Characterizing the sample complexity of private learners
• What Can We Learn Privately?
• Efficient noise-tolerant learning from statistical queries
• Bounds on the Sample Complexity for Private Learning and Private Data Release
• Learnability and the Vapnik-Chervonenkis dimension
• The Differential Privacy Frontier (Extended Abstract)
• A theory of the learnable
• Computational limitations on learning from examples
• Foundations of Cryptography
• On the complexity of differentially private data release
• Probability Inequalities for Sums of Bounded Random Variables
• A learning theory approach to noninteractive database privacy
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
• Theory of Cryptography