Timezone: »
Poster
DRIVE: One-bit Distributed Mean Estimation
Shay Vargaftik · Ran Ben-Basat · Amit Portnoy · Gal Mendelson · Yaniv Ben-Itzhak · Michael Mitzenmacher
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.
Author Information
Shay Vargaftik (VMware Research)
Ran Ben-Basat (University College London)
Amit Portnoy (Ben-Gurion University of the Negev)
Gal Mendelson (Stanford)
Yaniv Ben-Itzhak (VMware Research)
Michael Mitzenmacher (Harvard University)
More from the Same Authors
-
2018 Poster: A Model for Learned Bloom Filters and Optimizing by Sandwiching »
Michael Mitzenmacher -
2018 Poster: A Bayesian Nonparametric View on Count-Min Sketch »
Diana Cai · Michael Mitzenmacher · Ryan Adams -
2016 Poster: Quantized Random Projections and Non-Linear Estimation of Cosine Similarity »
Ping Li · Michael Mitzenmacher · Martin Slawski