Coordinate-Descent Diffusion Learning by Networked Agents

11 Oct 2017 Wang Chengcheng Zhang Yonggang Ying Bicheng Sayed Ali H.

This work examines the mean-square error performance of diffusion stochastic algorithms under a generalized coordinate-descent scheme. In this setting, the adaptation step by each agent is limited to a random subset of the coordinates of its stochastic gradient vector... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Categories


  • MULTIAGENT SYSTEMS
  • DISTRIBUTED, PARALLEL, AND CLUSTER COMPUTING
  • SYSTEMS AND CONTROL