Distributed Fixed Point Methods with Compressed Iterates
Machine Learning
2019-12-23 v1 Distributed, Parallel, and Cluster Computing
Numerical Analysis
Numerical Analysis
Optimization and Control
Abstract
We propose basic and natural assumptions under which iterative optimization methods with compressed iterates can be analyzed. This problem is motivated by the practice of federated learning, where a large model stored in the cloud is compressed before it is sent to a mobile device, which then proceeds with training based on local data. We develop standard and variance reduced methods, and establish communication complexity bounds. Our algorithms are the first distributed methods with compressed iterates, and the first fixed point methods with compressed iterates.
Cite
@article{arxiv.1912.09925,
title = {Distributed Fixed Point Methods with Compressed Iterates},
author = {Sélim Chraibi and Ahmed Khaled and Dmitry Kovalev and Peter Richtárik and Adil Salim and Martin Takáč},
journal= {arXiv preprint arXiv:1912.09925},
year = {2019}
}
Comments
15 pages, 4 algorithms, 4 Theorems