OCLGDec 21, 2016

Distributed Dictionary Learning

arXiv:1612.07335v110 citations
Originality Highly original
AI Analysis

This addresses the challenge of processing large-scale, distributed data efficiently in scenarios like big-data applications, offering a solution for resource-limited or privacy-sensitive environments.

The paper tackles the problem of distributed dictionary learning over multi-agent networks with time-varying connectivity, developing a novel algorithmic framework that ensures asymptotic convergence, which is the first such provable method for this class of problems.

The paper studies distributed Dictionary Learning (DL) problems where the learning task is distributed over a multi-agent network with time-varying (nonsymmetric) connectivity. This formulation is relevant, for instance, in big-data scenarios where massive amounts of data are collected/stored in different spatial locations and it is unfeasible to aggregate and/or process all the data in a fusion center, due to resource limitations, communication overhead or privacy considerations. We develop a general distributed algorithmic framework for the (nonconvex) DL problem and establish its asymptotic convergence. The new method hinges on Successive Convex Approximation (SCA) techniques coupled with i) a gradient tracking mechanism instrumental to locally estimate the missing global information; and ii) a consensus step, as a mechanism to distribute the computations among the agents. To the best of our knowledge, this is the first distributed algorithm with provable convergence for the DL problem and, more in general, bi-convex optimization problems over (time-varying) directed graphs.

Foundations

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

Your Notes