English

Coordinate-Descent Diffusion Learning by Networked Agents

Multiagent Systems 2017-10-12 v2 Distributed, Parallel, and Cluster Computing Systems and Control

Abstract

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. The selection of coordinates varies randomly from iteration to iteration and from agent to agent across the network. Such schemes are useful in reducing computational complexity at each iteration in power-intensive large data applications. They are also useful in modeling situations where some partial gradient information may be missing at random. Interestingly, the results show that the steady-state performance of the learning strategy is not always degraded, while the convergence rate suffers some degradation. The results provide yet another indication of the resilience and robustness of adaptive distributed strategies.

Keywords

Cite

@article{arxiv.1607.01838,
  title  = {Coordinate-Descent Diffusion Learning by Networked Agents},
  author = {Chengcheng Wang and Yonggang Zhang and Bicheng Ying and Ali H. Sayed},
  journal= {arXiv preprint arXiv:1607.01838},
  year   = {2017}
}

Comments

Accepted for publication

R2 v1 2026-06-22T14:47:43.075Z