Differentially Private Correlation Clustering

Authors: Mark Bun, Marek Elias, Janardhan Kulkarni

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We propose an algorithm that achieves subquadratic additive error compared to the optimal cost. In contrast, straightforward adaptations of existing non-private algorithms all lead to a trivial quadratic error. Finally, we give a lower bound showing that any pure differentially private algorithm for correlation clustering requires additive error of Ω(n).
Researcher Affiliation Collaboration 1Boston University, Boston 2CWI, Amsterdam 3Microsoft Research, Redmond.
Pseudocode Yes The paper includes several algorithm blocks labeled 'Algorithm 1', 'Algorithm 2', 'Algorithm 3', 'Algorithm 4', 'Algorithm 5', and 'Algorithm 6'.
Open Source Code No The paper does not contain any explicit statement about releasing source code or provide a link to a code repository.
Open Datasets No The paper is theoretical and focuses on algorithm design and analysis, not empirical studies involving datasets. Therefore, it does not provide information about publicly available or open datasets for training.
Dataset Splits No The paper is theoretical and focuses on algorithm design and analysis, not empirical studies involving datasets. Therefore, it does not provide information about training/test/validation dataset splits.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not provide specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not provide details about an experimental setup, hyperparameters, or system-level training settings.