NeurIPS 2021poster49 citations
DRIVE: One-bit Distributed Mean Estimation
Shay Vargaftik, Ran Ben-Basat, Amit Portnoy, Gal Mendelson, Yaniv Ben-Itzhak, Michael Mitzenmacher
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.
Distributed Mean EstimationStochastic ApproximationFederated LearningDistributed LeaningCommunication EfficiencyBandwidth Reduction
BibTeX
@inproceedings{
vargaftik2021drive,
title={{DRIVE}: One-bit Distributed Mean Estimation},
author={Shay Vargaftik and Ran Ben-Basat and Amit Portnoy and Gal Mendelson and Yaniv Ben-Itzhak and Michael Mitzenmacher},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=KXRTmcv3dQ8}
}