Wishart Mechanism for Differentially Private Principal Components Analysis

Authors: Wuxuan Jiang, Cong Xie, Zhihua Zhang

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this section, we are going to conduct theoretical analysis of Algorithms 1 and 2 under the framework of differential private matrix publishing. The theoretical support has two parts: privacy and utility guarantee. The former is the essential requirement for privacy-preserving algorithms and the latter tells how well the algorithm works against a nonprivate version.
Researcher Affiliation Academia Wuxuan Jiang, Cong Xie and Zhihua Zhang Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China
Pseudocode Yes Algorithm 1 Laplace input perturbation
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not mention using or providing access to any dataset for training or evaluation.
Dataset Splits No The paper is theoretical and does not describe experimental setups involving dataset splits like training, validation, or testing.
Hardware Specification No The paper does not mention any specific hardware used for experiments, as it is a theoretical paper.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters or training configurations.