Research map / Federated learning and privacy / Differential privacy
Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning
Tianhao Wang, Saeed Mahloujifar, Shouda Wang, Ruoxi Jia, Prateek Mittal
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use PTR instead of Gaussian noise scaled to global sensitivity for private trimmed-mean SGD | TSGD · MNIST, all reported corruption settings and privacy budgets | accuracy: 87.53% -> 91.43%; 81.31% -> 92.8% | Improved |
| Use PTR instead of Gaussian noise scaled to global sensitivity for private trimmed-mean SGD | TSGD · CIFAR10, all reported corruption settings and privacy budgets | accuracy: 57.94% -> 58.92%; 58.82% -> 60.13% | Improved |
| Use PTR instead of Gaussian noise scaled to global sensitivity for private trimmed-mean SGD | TSGD · EMNIST, all reported corruption settings and privacy budgets | accuracy: 72.94% -> 76.44%; 79.15% -> 81.02% | Improved |
| Use the white-box subsampled PTR RDP bound instead of the black-box general subsampling bound | Subsampled PTR privacy analysis · Poisson subsampling; privacy amplification bound | RDP bound tightness | Improved |
| Convert the PTR RDP bound to (ε, δ)-DP instead of directly analyzing (ε, δ)-DP | PTR · Privacy guarantee when δ0 is close to target δ | ε privacy parameter | Improved |
Closest papers by meaning
- Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement (NeurIPS 2024 · similarity 0.87)
- Differentially Private Model Merging (NeurIPS 2026 · similarity 0.86)
- Certification for Differentially Private Prediction in Gradient-Based Training (ICML 2025 · similarity 0.85)
- Online Sensitivity Optimization in Differentially Private Learning (AAAI 2024 · similarity 0.85)
- Auditing Private Prediction (ICML 2024 · similarity 0.85)
- Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
