Poission Subsampled Rényi Differential Privacy

By Yuqing Zhu, Yu-Xiang Wang. 2019

107 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yu-Xiang Wang
2. Om Thakkar
3. Yuqing Zhu
4. Abhradeep Thakurta
5. Shuang Song
6. Peter Kairouz
7. Chen Chen
8. B. McMahan

Citations in the corpus

• Practical and Private (Deep) Learning without Sampling or Shuffling (2021, methodology): “2One can also create a mini-batch with Poisson sampling [1, 49, 73], except the batch size is now a random variable.”
• Private-kNN: Practical Differential Privacy for Computer Vision (2020, methodology): “For the latter, we can readily apply the tight bound of the subsampled Gaussian mechanism from [30].”
• Understanding Gradient Clipping in Private SGD: A Geometric Perspective (2020, background): “, 2019] and Poisson subsampling [Zhu and Wang, 2019] have also been proposed.”
• Stochastic Adaptive Line Search for Differentially Private Optimization (2020, methodology): “Rényi differential privacy (RDP) is a recent privacy framework proposed in [3], which stands between pure and approximate DP, and its privacy amplification lemma is presented in [13].”