DRIVE: One-Bit Distributed Mean Estimation
Abstract
We consider the problem where $n$ clients transmit $d$-dimensional real-valued vectors using $d(1+o(1))$ bits each, in a manner that allows the receiver to approximately reconstruct their mean. Such compression problems naturally arise in distributed and federated learning. We provide novel mathematical results and derive computationally efficient algorithms that are more accurate than previous compression techniques. We evaluate our methods on a collection of distributed and federated learning tasks, using a variety of datasets, and show a consistent improvement over the state of the art.
Cite
Text
Vargaftik et al. "DRIVE: One-Bit Distributed Mean Estimation." Neural Information Processing Systems, 2021.Markdown
[Vargaftik et al. "DRIVE: One-Bit Distributed Mean Estimation." Neural Information Processing Systems, 2021.](https://mlanthology.org/neurips/2021/vargaftik2021neurips-drive/)BibTeX
@inproceedings{vargaftik2021neurips-drive,
title = {{DRIVE: One-Bit Distributed Mean Estimation}},
author = {Vargaftik, Shay and Ben-Basat, Ran and Portnoy, Amit and Mendelson, Gal and Ben-Itzhak, Yaniv and Mitzenmacher, Michael},
booktitle = {Neural Information Processing Systems},
year = {2021},
url = {https://mlanthology.org/neurips/2021/vargaftik2021neurips-drive/}
}