Differentially Private Equivalence Testing for Continuous Distributions and Applications

Authors: Or Sheffet, Daniel Omer

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We present the first algorithm for testing equivalence between two continuous distributions using differential privacy (DP). Our algorithm is a private version of the algorithm of Diakonikolas et al [16].
Researcher Affiliation Academia Daniel Omer Math. Dept. Bar-Ilan University omerdan@biu.ac.il Or Sheffet Faculty of Engineering Bar-Ilan University or.sheffet@biu.ac.il
Pseudocode Yes Algorithm 1 Private Equivalence Tester and Algorithm 2 Test Closeness-(N, m, X, Y , α, ϵ , δ , δ)
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 focuses on algorithm design and proofs, assuming oracle access to distributions for theoretical analysis rather than using specific publicly available datasets for training.
Dataset Splits No As the paper presents a theoretical framework without empirical studies, it does not specify training, validation, or test dataset splits.
Hardware Specification No The paper focuses on theoretical contributions and does not describe any experimental setup or the specific hardware used.
Software Dependencies No The paper is theoretical and does not detail any software dependencies or their specific version numbers required for replication of experiments.
Experiment Setup No The paper describes a theoretical algorithm and its proofs without conducting empirical experiments; therefore, it does not include details on experimental setup or hyperparameters.