English

Linear convergence in optimization over directed graphs with row-stochastic matrices

Optimization and Control 2017-11-01 v4

Abstract

This paper considers a distributed optimization problem over a multi-agent network, in which the objective function is a sum of individual cost functions at the agents. We focus on the case when communication between the agents is described by a \emph{directed} graph. Existing distributed optimization algorithms for directed graphs require at least the knowledge of the neighbors' out-degree at each agent (due to the requirement of column-stochastic matrices). In contrast, our algorithm requires no such knowledge. Moreover, the proposed algorithm achieves the best known rate of convergence for this class of problems, O(μk)O(\mu^k) for 0<μ<10<\mu<1, where kk is the number of iterations, given that the objective functions are strongly-convex and have Lipschitz-continuous gradients. Numerical experiments are also provided to illustrate the theoretical findings.

Keywords

Cite

@article{arxiv.1611.06160,
  title  = {Linear convergence in optimization over directed graphs with row-stochastic matrices},
  author = {Chenguang Xi and Van Sy Mai and Ran Xin and Eyad H. Abed and Usman A. Khan},
  journal= {arXiv preprint arXiv:1611.06160},
  year   = {2017}
}

Comments

arXiv admin note: text overlap with arXiv:1607.04757

R2 v1 2026-06-22T16:57:15.557Z