English

Exact Diffusion for Distributed Optimization and Learning --- Part I: Algorithm Development

Optimization and Control 2017-12-05 v2

Abstract

This work develops a distributed optimization strategy with guaranteed exact convergence for a broad class of left-stochastic combination policies. The resulting exact diffusion strategy is shown in Part II to have a wider stability range and superior convergence performance than the EXTRA strategy. The exact diffusion solution is applicable to non-symmetric left-stochastic combination matrices, while many earlier developments on exact consensus implementations are limited to doubly-stochastic matrices; these latter matrices impose stringent constraints on the network topology. The derivation of the exact diffusion strategy in this work relies on reformulating the aggregate optimization problem as a penalized problem and resorting to a diagonally-weighted incremental construction. Detailed stability and convergence analyses are pursued in Part II and are facilitated by examining the evolution of the error dynamics in a transformed domain. Numerical simulations illustrate the theoretical conclusions.

Keywords

Cite

@article{arxiv.1702.05122,
  title  = {Exact Diffusion for Distributed Optimization and Learning --- Part I: Algorithm Development},
  author = {Kun Yuan and Bicheng Ying and Xiaochuan Zhao and Ali H. Sayed},
  journal= {arXiv preprint arXiv:1702.05122},
  year   = {2017}
}

Comments

15 pages; 12 figures; Submitted for publication