NeurIPS 2020poster138 citations
Breaking the Communication-Privacy-Accuracy Trilemma
Wei-Ning Chen, Peter Kairouz, Ayfer Ozgur
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.
BibTeX
@inproceedings{NEURIPS2020_222afbe0,
author = {Chen, Wei-Ning and Kairouz, Peter and Ozgur, Ayfer},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {3312--3324},
publisher = {Curran Associates, Inc.},
title = {Breaking the Communication-Privacy-Accuracy Trilemma},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/222afbe0d68c61de60374b96f1d86715-Paper.pdf},
volume = {33},
year = {2020}
}