Fast Decentralized Optimization over Networks
Abstract
The present work introduces the hybrid consensus alternating direction method of multipliers (H-CADMM), a novel framework for optimization over networks which unifies existing distributed optimization approaches, including the centralized and the decentralized consensus ADMM. H-CADMM provides a flexible tool that leverages the underlying graph topology in order to achieve a desirable sweet-spot between node-to-node communication overhead and rate of convergence -- thereby alleviating known limitations of both C-CADMM and D-CADMM. A rigorous analysis of the novel method establishes linear convergence rate, and also guides the choice of parameters to optimize this rate. The novel hybrid update rules of H-CADMM lend themselves to "in-network acceleration" that is shown to effect considerable -- and essentially "free-of-charge" -- performance boost over the fully decentralized ADMM. Comprehensive numerical tests validate the analysis and showcase the potential of the method in tackling efficiently, widely useful learning tasks.
Keywords
Cite
@article{arxiv.1804.02425,
title = {Fast Decentralized Optimization over Networks},
author = {Meng Ma and Athanasios N. Nikolakopoulos and Georgios B. Giannakis},
journal= {arXiv preprint arXiv:1804.02425},
year = {2018}
}
Comments
fix error in remark 4; clean up algorithms 2