Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and Inference

Authors: Ce Zhang, Yixin Han, Yafei Wang, Xiaodong Yan, Linglong Kong, Ting Li, Bei Jiang

ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive simulation studies and real-world applications confirm that our methods outperform existing approaches in terms of precise estimation, privacy protection, and reliable inference.
Researcher Affiliation Academia 1Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, Canada 2School of Mathematics and Statistics, Xi an Jiaotong University, Xi an, China 3Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China. Correspondence to: Bei Jiang <EMAIL>, Ting Li <EMAIL>.
Pseudocode No The paper contains mathematical derivations, theoretical results, and proofs, but no clearly labeled pseudocode or algorithm blocks are present.
Open Source Code No The paper does not contain an explicit statement about releasing source code, nor does it provide a link to a code repository.
Open Datasets Yes In Section 6, we apply our proposed method to a real-world dataset focused on measuring plagiarism among students, as detailed in (Jann et al., 2012).
Dataset Splits Yes For our analysis, the dataset was divided into two parts: 75% of the data was used to train the model, while the remaining 25% was reserved for testing.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies or library versions used for implementation or experimentation.
Experiment Setup Yes We set d = 4, sample size n = 105 and fix β = (1, 0.25, 0, 0.5) . Two covariate structures are considered... We set the nominal significant level α = 0.05. We study both the ε-DP (δ = 0) and (ε, δ)-DP (δ = 10 5). All simulation results are based on B = 500 independent replications...