NeurIPS 2020poster37 citations
Decentralized Accelerated Proximal Gradient Descent
Haishan Ye, Ziang Zhou, Luo Luo, Tong Zhang
Abstract
Decentralized optimization has wide applications in machine learning, signal processing, and control. In this paper, we study the decentralized composite optimization problem with a non-smooth regularization term. Many proximal gradient based decentralized algorithms have been proposed in the past. However, these algorithms do not achieve near optimal computational complexity and communication complexity. In this paper, we propose a new method which establishes the optimal computational complexity and a near optimal communication complexity. Our empirical study shows that the proposed algorithm outperforms existing state-of-the-art algorithms.
BibTeX
@inproceedings{NEURIPS2020_d4b5b5c1,
author = {Ye, Haishan and Zhou, Ziang and Luo, Luo and Zhang, Tong},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {18308--18317},
publisher = {Curran Associates, Inc.},
title = {Decentralized Accelerated Proximal Gradient Descent},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/d4b5b5c16df28e61124e13181db7774c-Paper.pdf},
volume = {33},
year = {2020}
}