Breaking the Communication-Privacy-Accuracy Trilemma

Abstract

Two major challenges in distributed learning and estimation are 1) preserving the privacy of the local samples; and 2) communicating them efficiently to a central server, while achieving high accuracy for the end-to-end task. While there has been significant interest in addressing each of these challenges separately in the recent literature, treatments that simultaneously address both challenges are still largely missing. In this paper, we develop novel encoding and decoding mechanisms that simultaneously achieve optimal privacy and communication efficiency in various canonical settings.

Cite

Text

Chen et al. "Breaking the Communication-Privacy-Accuracy Trilemma." Neural Information Processing Systems, 2020.

Markdown

[Chen et al. "Breaking the Communication-Privacy-Accuracy Trilemma." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/chen2020neurips-breaking/)

BibTeX

@inproceedings{chen2020neurips-breaking,
  title     = {{Breaking the Communication-Privacy-Accuracy Trilemma}},
  author    = {Chen, Wei-Ning and Kairouz, Peter and Ozgur, Ayfer},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/chen2020neurips-breaking/}
}