Improving the Utility of Differentially Private Clustering through Dynamical Processing. (arXiv:2304.13886v1 [cs.LG])

This study aims to alleviate the trade-off between utility and privacy in the
task of differentially private clustering. Existing works focus on simple
clustering methods, which show poor clustering performance for non-convex
clusters. By utilizing Morse theory, we hierarchically connect the Gaussian
sub-clusters to fit complex cluster distributions. Because differentially
private sub-clusters are obtained through the existing methods, the proposed
method causes little or no additional privacy loss. We provide a theoretical
background that implies that the proposed method is …

cluster clustering clusters connect distributions focus loss morse non performance poor privacy private simple study task theory trade utility