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. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Optimization and Control | Numerical tests,Mathematical optimization,Decentralized optimization,Acceleration,Rate of convergence,Topological graph theory,Mathematics |
DocType | Volume | Citations |
Journal | abs/1804.02425 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Meng Ma | 1 | 0 | 2.37 |
Athanasios N. Nikolakopoulos | 2 | 59 | 9.02 |
G. B. Giannakis | 3 | 11464 | 1206.47 |