Locally Private k-Means in One Round

Alisa Chang, Badih Ghazi, Ravi Kumar, Pasin Manurangsi

Abstract

We provide an approximation algorithm for k-means clustering in the one-round (aka non-interactive) local model of differential privacy (DP). This algorithm achieves an approximation ratio arbitrarily close to the best non private approximation algorithm, improving upon previously known algorithms that only guarantee large (constant) approximation ratios. Furthermore, this is the first constant-factor approximation algorithm for k-means that requires only one round of communication in the local DP model, positively resolving an open question of Stemmer (SODA 2020). Our algorithmic framework is quite flexible; we demonstrate this by showing that it also yields a similar near-optimal approximation algorithm in the (one-round) shuffle DP model.
BibTeX
@inproceedings{chang2021locally,
  author = {Alisa Chang and Badih Ghazi and Ravi Kumar and Pasin Manurangsi},
  title = {{Locally Private k-Means in One Round}},
  booktitle = {International Conference on Machine Learning},
  year = {2021},
  url = {https://openreview.net/forum?id=SZ4M6jJlzX5},
}

Loading related content...

Figure