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 | DOI | Venue |
---|---|---|
2018 | 10.1186/s13634-018-0589-x | EURASIP Journal on Advances in Signal Processing |
Keywords | Field | DocType |
ADMM,Distributed optimization,Decentralized learning,Hybrid,Consensus | Numerical tests,Mathematical optimization,Decentralized optimization,Computer science,Acceleration,Rate of convergence,Artificial intelligence,Topological graph theory,Machine learning | Journal |
Volume | Issue | ISSN |
2018 | 1 | 1687-6180 |
Citations | PageRank | References |
0 | 0.34 | 29 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Meng Ma | 1 | 82 | 12.29 |
Athanasios N. Nikolakopoulos | 2 | 59 | 9.02 |
Georgios B. Giannakis | 3 | 0 | 0.34 |