| Autor: |
Meng Ma, Athanasios N. Nikolakopoulos, Georgios B. Giannakis |
| Jazyk: |
angličtina |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
EURASIP Journal on Advances in Signal Processing, Vol 2018, Iss 1, Pp 1-17 (2018) |
| Druh dokumentu: |
article |
| ISSN: |
1687-6180 |
| DOI: |
10.1186/s13634-018-0589-x |
| Popis: |
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. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
Full text from SpringerLink