RLC Circuits-Based Distributed Mirror Descent Method

Yue Yu, Behcet Acikmese

Research output: Contribution to journalArticlepeer-review

11 Scopus citations

Abstract

We consider distributed optimization with smooth convex objective functions defined on an undirected connected graph. Inspired by mirror descent mehod and RLC circuits, we propose a novel distributed mirror descent method. Compared with mirror-prox method, our algorithm achieves the same $\mathcal {O}$ (/k$) iteration complexity with only half the computation cost per iteration. We further extend our results to cases where a) gradients are corrupted by stochastic noise, and b) objective function is composed of both smooth and non-smooth terms. We demonstrate our theoretical results via numerical experiments.

Original languageEnglish (US)
Article number8993740
Pages (from-to)548-553
Number of pages6
JournalIEEE Control Systems Letters
Volume4
Issue number3
DOIs
StatePublished - Jul 2020
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Keywords

  • Distributed optimization
  • mirror descent

Fingerprint

Dive into the research topics of 'RLC Circuits-Based Distributed Mirror Descent Method'. Together they form a unique fingerprint.

Cite this