Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences

Authors: Borja Balle, Gilles Barthe, Marco Gaboardi

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper we present a general method that recovers and improves prior analyses, yields lower bounds and derives new instances of privacy amplification by subsampling. Our method leverages a characterization of differential privacy as a divergence which emerged in the program verification community.
Researcher Affiliation Collaboration Borja Balle Amazon Research pigem@amazon.co.uk Gilles Barthe IMDEA Software Institute gilles.barthe@imdea.org Marco Gaboardi University at Buffalo, SUNY gaboardi@buffalo.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper is theoretical and does not describe the use of datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not involve dataset splits for reproduction.
Hardware Specification No The paper does not provide specific hardware details for running experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper is theoretical and does not describe experimental setup details like hyperparameters or training configurations.