Differentially-Private Sublinear-Time Clustering

Authors: Jeremiah Blocki, Elena Grigorescu, Tamalika Mukherjee
Published: 2021-12-27

Source: https://arxiv.org/abs/2112.13751

PDF: https://arxiv.org/pdf/2112.13751

Labels Predicted by AI

サンプリング手法 収束保証 プライバシーリスク管理

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Clustering is an essential primitive in unsupervised machine learning. We bring forth the problem of sublinear-time differentially-private clustering as a natural and well-motivated direction of research. We combine the k-means and k-median sublinear-time results of Mishra et al. (SODA, 2001) and of Czumaj and Sohler (Rand. Struct. and Algorithms, 2007) with recent results on private clustering of Balcan et al. (ICML 2017), Gupta et al. (SODA, 2010) and Ghazi et al. (NeurIPS, 2020) to obtain sublinear-time private k-means and k-median algorithms via subsampling. We also investigate the privacy benefits of subsampling for group privacy.