MLSPSep 22, 2017

Estimate Exchange over Network is Good for Distributed Hard Thresholding Pursuit

arXiv:1709.07731v112 citations
Originality Synthesis-oriented
AI Analysis

This work addresses communication efficiency in distributed sparse signal learning, but it is incremental as it analyzes an existing algorithm rather than introducing a new one.

The paper tackles the problem of learning sparse signals over networks with limited communication by analyzing an existing iterative algorithm that exchanges intermediate estimates. The result shows competitive performance compared to an alternative algorithm that requires more information exchange, supported by theoretical convergence analysis and simulations.

We investigate an existing distributed algorithm for learning sparse signals or data over networks. The algorithm is iterative and exchanges intermediate estimates of a sparse signal over a network. This learning strategy using exchange of intermediate estimates over the network requires a limited communication overhead for information transmission. Our objective in this article is to show that the strategy is good for learning in spite of limited communication. In pursuit of this objective, we first provide a restricted isometry property (RIP)-based theoretical analysis on convergence of the iterative algorithm. Then, using simulations, we show that the algorithm provides competitive performance in learning sparse signals vis-a-vis an existing alternate distributed algorithm. The alternate distributed algorithm exchanges more information including observations and system parameters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes