Private data release via learning thresholds

zbMATH Open1421.68038arXiv1107.2444MaRDI QIDQ5743387FDOQ5743387

Authors: Moritz Hardt, Guy N. Rothblum, Rocco A. Servedio 

Publication date: 10 May 2019

Full work available at URL: https://arxiv.org/abs/1107.2444

Recommendations

• Faster private release of marginals on small databases
• Faster algorithms for privately releasing marginals
• The algorithmic foundations of differential privacy

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Database theory (68P15) Authentication, digital signatures and secret sharing (94A62)

Cites Work

• On the learnability of discrete distributions
• Learning Decision Trees Using the Fourier Spectrum
• Theory of Cryptography
• Interactive privacy via the median mechanism
• The price of privately releasing contingency tables and the spectra of random matrices with correlated rows
• On the complexity of differentially private data release, efficient algorithms and hardness results
• Title not available (Why is that?)
• On PAC learning algorithms for rich Boolean function classes
• A theory of the learnable
• Title not available (Why is that?)
• An efficient membership-query algorithm for learning DNF with respect to the uniform distribution
• Learning DNF in time \(2^{\widetilde O(n^{1/3})}\)
• Learning intersections and thresholds of halfspaces
• What can we learn privately?
• Learnability beyond AC ⁰
• The Intersection of Two Halfspaces Has High Threshold Degree
• Pcps and the hardness of generating private synthetic data
• Title not available (Why is that?)

Cited In (22)

• PCPs and the hardness of generating synthetic data
• Empirical risk minimization in the non-interactive local model of differential privacy
• Learning Privately with Labeled and Unlabeled Examples
• Efficient algorithms for privately releasing marginals via convex relaxations
• PrivBayes. Private data release via Bayesian networks
• Private analysis of graph structure
• The algorithmic foundations of differential privacy
• The power of linear reconstruction attacks
• Exploiting metric structure for efficient private query release
• Differentially private learning of geometric concepts
• Nearly optimal private convolution
• Answering \(n^2+o(1)\) counting queries with differential privacy is hard
• Differentially private data releasing for smooth queries
• Fast private data release algorithms for sparse queries
• Differential privacy: getting more for less
• Pure differential privacy for rectangle queries via private partitions
• Efficient and secure outsourcing of differentially private data publication
• Differential privacy on finite computers
• Answering \(n^{2+o(1)}\) counting queries with differential privacy is hard
• A learning theory approach to noninteractive database privacy
• Using convex relaxations for efficiently and privately releasing marginals (extended abstract)
• Faster algorithms for privately releasing marginals

This page was built for publication: Private data release via learning thresholds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5743387)