On Sparse Linear Regression in the Local Differential Privacy Model

Authors: Di Wang, Jinhui Xu

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on real world and synthetic datasets confirm our theoretical analysis.
Researcher Affiliation Academia 1Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, USA. Emails: {dwang45,jinhui}@buffalo.edu.
Pseudocode Yes Algorithm 1 LDP-IHT
Open Source Code No The paper does not contain any explicit statement about releasing source code for the methodology described, nor does it provide a link to a code repository.
Open Datasets No The paper mentions using a 'real world dataset Covertype' but does not provide a formal citation, link, or repository information for accessing it. It also uses synthetic data whose generation process is described, but no public access is provided.
Dataset Splits No The paper describes data generation but does not provide specific training/validation/test dataset splits, percentages, or sample counts, nor does it mention cross-validation or standard benchmark splits.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments, such as exact GPU/CPU models, processor types, or memory amounts.
Software Dependencies No The paper mentions using 'TFOCS' as a method for choosing the step size but does not provide specific version numbers for this or any other software dependencies.
Experiment Setup Yes We assume 퐶= 0.05 in our experiment. We run algorithms Label-LDP-IHT with 휂= 0.2 or 휂= 0.1, 푠= 푠 , 푇= log 푛 푝 , 훿= 10 3 and a random normal Gaussian vector as the initial point to obtain 휃푇.