Adapt-Align-Combine for diffusion-based distributed dictionary learning
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 463-467
Abstract
Diffusion-based distributed dictionary learning methods are studied in this work. We consider the classical mixed l2-l1 cost function, that employs an l2 representation error term and an l1 sparsity promoting regularizer. First, we observe that this cost function suffers from an inherent permutation ambiguity. This ambiguity may deteriorate significantly the performance of diffusion-based schemes, since the involved combination step may combine different atoms even when the same atoms exist at all dictionaries. Thus, we propose to align the dictionaries prior to the combination step. Furthermore, we define a new problem, that we call the node-specific distributed dictionary learning problem. The proposed Adapt-Align-Combine algorithm enjoys increased convergence rate as compared with a scheme that does not align the dictionaries prior to the combination. Simulation results support our findings.Keywords
This publication has 15 references indexed in Scilit:
- A convergence analysis of distributed dictionary learning based on the K-SVD algorithm2015
- Dictionary Learning Over Distributed ModelsIEEE Transactions on Signal Processing, 2014
- Distributed Dictionary Learning for Sparse Representation in Sensor NetworksIEEE Transactions on Image Processing, 2014
- Adaptive NetworksProceedings of the IEEE, 2014
- A decentralized approach to generalized power system state estimation2013
- Cloud K-SVD: Computing data-adaptive representations in the cloud2013
- Large-scale distributed non-negative sparse coding and sparse dictionary learning2012
- Diffusion LMS Strategies for Distributed EstimationIEEE Transactions on Signal Processing, 2009
- The Linear Assignment Problem1992
- Algorithms for the Assignment and Transportation ProblemsJournal of the Society for Industrial and Applied Mathematics, 1957