Distributed Mean Estimation for Multi-Message Shuffled Privacy

Abstract

In this paper, we study distributed mean estimation (DME) under privacy and communication constraints in the multi-message shuffle model. We propose communication-efficient algorithms for privately estimating the mean of bound $\ell_2$-norm and $\ell_{\infty}$-norm norm vectors. Our algorithms are designed by giving unequal privacy at different resolutions of the vector (through binary expansion) and appropriately combining it with co-ordinate sampling. We show that our proposed algorithms achieve order-optimal privacy-communication-performance trade-offs.

Cite

Text

Girgis and Diggavi. "Distributed Mean Estimation for Multi-Message Shuffled Privacy." ICML 2023 Workshops: FL, 2023.

Markdown

[Girgis and Diggavi. "Distributed Mean Estimation for Multi-Message Shuffled Privacy." ICML 2023 Workshops: FL, 2023.](https://mlanthology.org/icmlw/2023/girgis2023icmlw-distributed/)

BibTeX

@inproceedings{girgis2023icmlw-distributed,
  title     = {{Distributed Mean Estimation for Multi-Message Shuffled Privacy}},
  author    = {Girgis, Antonious M. and Diggavi, Suhas},
  booktitle = {ICML 2023 Workshops: FL},
  year      = {2023},
  url       = {https://mlanthology.org/icmlw/2023/girgis2023icmlw-distributed/}
}