15
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Distributed Dictionary Learning

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          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.

          Related collections

          Most cited references12

          • Record: found
          • Abstract: not found
          • Article: not found

          Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Distributed average consensus with least-mean-square deviation

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Sparse principal component analysis via regularized low rank matrix approximation

                Bookmark

                Author and article information

                Journal
                2016-12-21
                Article
                1612.07335
                34c6bbdd-e0c2-40c5-b1a6-2c9f0505d3f2

                http://creativecommons.org/licenses/by/4.0/

                History
                Custom metadata
                math.OC cs.LG

                Numerical methods,Artificial intelligence
                Numerical methods, Artificial intelligence

                Comments

                Comment on this article