Tighter Privacy Analysis for Truncated Poisson Sampling
Not on the map. Why?
Abstract (arXiv)
We give a new privacy amplification analysis for truncated Poisson sampling, a Poisson sampling variant that truncates a batch if it exceeds a given maximum batch size.
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Aug 2025.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2025: 1; 2026: 4.
5 papers.
- 2026JAX-Privacy: A library for differentially private machine learningcited by 3
- 2026Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?cited by 2
- 2025Correlating Cross-Iteration Noise for DP-SGD using Model Curvaturecited by 1
- 2026ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?cited by 0
- 2026Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGDcited by 0
- 2026Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD7 Oct 2026
- 2026ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?1 Jun 2026
- 2026Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?8 May 2026
- 2026JAX-Privacy: A library for differentially private machine learning19 Feb 2026
- 2025Correlating Cross-Iteration Noise for DP-SGD using Model Curvature6 Oct 2025