Differentially-Private Clustering Of Easy Instances

INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139(2021)

引用 17|浏览94
暂无评分
摘要
Clustering is a fundamental problem in data analysis. In differentially private clustering, the goal is to identify k cluster centers without disclosing information on individual data points. Despite significant research progress, the problem had so far resisted practical solutions. In this work we aim at providing simple implementable differentially private clustering algorithms that provide utility when the data is "easy," e.g., when there exists a significant separation between the clusters.We propose a framework that allows us to apply non-private clustering algorithms to the easy instances and privately combine the results. We are able to get improved sample complexity bounds in some cases of Gaussian mixtures and k-means. We complement our theoretical analysis with an empirical evaluation on synthetic data.
更多
查看译文
关键词
clustering,differentially-private
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要