NeurIPS 2019 accepted papers on Federated learning and privacy
29 of the 1,429 papers accepted at NeurIPS 2019 (2.0%) are on Federated learning and privacy, compared with 1.8% at NeurIPS 2018. They fall into 2 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Differential privacy · 26 papers
- Differential Privacy Has Disparate Impact on Model Accuracy (76 citations)
- Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces (34 citations)
- Differentially Private Bayesian Linear Regression (24 citations)
- Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation (21 citations)
- On Differentially Private Graph Sparsification and Applications (19 citations)
- Practical Differentially Private Top-k Selection with Pay-what-you-get Composition (19 citations)
- Differentially Private Algorithms for Learning Mixtures of Separated Gaussians (18 citations)
- Differentially Private Covariance Estimation (17 citations)
- Locally Private Gaussian Estimation (17 citations)
- Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy (14 citations)
- Limits of Private Learning with Access to Public Data (12 citations)
- Differentially Private Markov Chain Monte Carlo (10 citations)
and 14 more in the interactive map.
