Tighter Privacy Analysis for Truncated Poisson Sampling
Cryptography and Security
2025-08-22 v1
Authors:
Arun Ganesh
Abstract
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.
Keywords
Cite
@article{arxiv.2508.15089,
title = {Tighter Privacy Analysis for Truncated Poisson Sampling},
author = {Arun Ganesh},
journal= {arXiv preprint arXiv:2508.15089},
year = {2025}
}
Related papers
View all related →
Applications · Statistics
Accuracy Gains from Privacy Amplification Through Sampling for Differential Privacy
Jingchen Hu, Joerg Drechsler, Hang J. Kim
2022-02-22
Probability · Mathematics
Improving approximation error bounds via truncation
H. L. Gan
2017-05-02
Machine Learning · Computer Science
Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences
Borja Balle, Gilles Barthe, Marco Gaboardi
2018-11-26
Cryptography and Security · Computer Science
Personalized Privacy Amplification via Importance Sampling
Dominik Fay, Sebastian Mair, Jens Sjölund
2025-03-31
Machine Learning · Computer Science
Privacy amplification by random allocation
Vitaly Feldman, Moshe Shenfeld
2026-01-16
Machine Learning · Computer Science
Leveraging Randomness in Model and Data Partitioning for Privacy Amplification
Andy Dong, Wei-Ning Chen, Ayfer Ozgur
2025-06-03
Cryptography and Security · Computer Science
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition
Christian Janos Lebeda, Matthew Regehr, Gautam Kamath, Thomas Steinke
2025-04-09
Machine Learning · Computer Science
Privacy Amplification Via Bernoulli Sampling
Jacob Imola, Kamalika Chaudhuri
2021-10-20
Methodology · Statistics
Censored lifespans in a double-truncated sample: Maximum likelihood inference for the exponential distribution
Fiete Sieg, Anne-Marie Toparkus, Rafael Weissbach
2025-08-12
Methodology · Statistics
Truncating the Exponential with a Uniform Distribution
Rafael Weißbach, Dominik Wied
2021-10-19
Databases · Computer Science
Efficient and Private Approximations of Distributed Databases Calculations
Philip Derbeko, Shlomi Dolev, Ehud Gudes, Jeffrey D. Ullman
2016-05-23
Machine Learning · Computer Science
Differentially Private Online Bayesian Estimation With Adaptive Truncation
Sinan Yıldırım
2025-02-17
Machine Learning · Computer Science
How Private are DP-SGD Implementations?
Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar +3
2024-06-07
Chemical Physics · Physics
Stochastic Coupled Cluster Theory: Efficient Sampling of the Coupled Cluster Expansion
Charles J. C. Scott, Alex J. W. Thom
2018-08-14
Methodology · Statistics
Controlling Privacy Loss in Sampling Schemes: an Analysis of Stratified and Cluster Sampling
Mark Bun, Jörg Drechsler, Marco Gaboardi, Audra McMillan +1
2023-06-23
Machine Learning · Computer Science
Efficient privacy loss accounting for subsampling and random allocation
Vitaly Feldman, Moshe Shenfeld
2026-02-20
Instrumentation and Methods for Astrophysics · Physics
Coping with Selection Effects: A Primer on Regression with Truncated Data
Adam B. Mantz
2020-10-14
Cryptography and Security · Computer Science
Privacy Amplification via Shuffling: Unified, Simplified, and Tightened
Shaowei Wang, Yun Peng, Jin Li, Zikai Wen +4
2024-07-30
Machine Learning · Computer Science
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar +3
2024-11-08
Cryptography and Security · Computer Science
Improving Statistical Privacy by Subsampling
Dennis Breutigam, Rüdiger Reischuk
2025-04-16
Quantum Physics · Physics
Privacy amplification scheme based on composite coding
Wei Li, Shengmei Zhao
2021-09-16
Machine Learning · Computer Science
Privacy Amplification via Random Participation in Federated Learning
Burak Hasircioglu, Deniz Gunduz
2022-05-04
Statistics Theory · Mathematics
A Theory of Truncated Inverse Sampling
Xinjia Chen
2013-11-05
Cryptography and Security · Computer Science
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
Jan Schuchardt, Mihail Stoian, Arthur Kosmala, Stephan Günnemann
2024-11-04
Information Theory · Computer Science
Information Extraction Under Privacy Constraints
Shahab Asoodeh, Mario Diaz, Fady Alajaji, Tamás Linder
2016-01-19