The Composition Theorem for Differential Privacy

Authors: Peter Kairouz, Sewoong Oh, Pramod Viswanath

ICML 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our solution is complete: we prove an upper bound on the overall privacy level and construct a sequence of privatization mechanisms that achieves this bound. The key innovation is the introduction of an operational interpretation of differential privacy (involving hypothesis testing) and the use of new data processing inequalities.
Researcher Affiliation Academia Peter Kairouz KAIROUZ2@ILLINOIS.EDU ECE Department, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA Sewoong Oh SWOH@ILLINOIS.EDU IESE Department, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA Pramod Viswanath PRAMODV@ILLINOIS.EDU ECE Department, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement or link for the open-sourcing of the code for the described methodology.
Open Datasets No The paper is theoretical in nature, focusing on proofs and mathematical characterizations of differential privacy composition. It does not mention or use specific datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not describe experimental validation on data. Therefore, it does not specify any dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe experiments requiring specific hardware. No hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and focuses on mathematical proofs and characterizations. It does not describe any experimental setup details such as hyperparameters or training configurations.