English

Resilient Distributed Optimization

Optimization and Control 2023-03-22 v2 Systems and Control Systems and Control

Abstract

This paper considers a distributed optimization problem in the presence of Byzantine agents capable of introducing untrustworthy information into the communication network. A resilient distributed subgradient algorithm is proposed based on graph redundancy and objective redundancy. It is shown that the algorithm causes all non-Byzantine agents' states to asymptotically converge to the same optimal point under appropriate assumptions. A partial convergence rate result is also provided.

Keywords

Cite

@article{arxiv.2209.13095,
  title  = {Resilient Distributed Optimization},
  author = {Jingxuan Zhu and Yixuan Lin and Alvaro Velasquez and Ji Liu},
  journal= {arXiv preprint arXiv:2209.13095},
  year   = {2023}
}

Comments

This version fixes the incorrect statements of Proposition 3 and Theorem 2 in the last version