An adaptive projected subgradient approach to learning in diffusion networks

  • Authors:
  • Renato L. G. Cavalcante;Isao Yamada;Bernard Mulgrew

  • Affiliations:
  • Digital Communications Research Institute, Joint Research Institute for Signal and Image Processing, The University of Edinburgh, Edinburgh, U.K.;Department of Communications and Integrated Systems, Tokyo Institute of Technology, Sakaniwa and Yamada Laboratory, Tokyo, Japan;Digital Communications Research Institute, Joint Research Institute for Signal and Image Processing, The University of Edinburgh, Edinburgh, U.K.

  • Venue:
  • IEEE Transactions on Signal Processing
  • Year:
  • 2009

Quantified Score

Hi-index 35.68

Visualization

Abstract

We present an algorithm that minimizes asymptotically a sequence of nonnegative convex functions over diffusion networks. In the proposed algorithm, at each iteration the nodes in the network have only partial information of the cost function, but they are able to achieve consensus on a possible minimizer asymptotically. To account for possible node failures, position changes, and/or reachability problems (because of moving obstacles, jammers, etc.), the algorithm can cope with changing network topologies and cost functions, a desirable feature in online algorithms where information arrives sequentially. Many projection-based algorithms can be straightforwardly extended to (probabilistic) diffusion networks with the proposed scheme. The system identification problem in distributed networks is given as one example of a possible application.