Dynamic Regret Analysis for Event-Triggered Distributed Online Optimization Algorithm

Makoto YAMASHITA  Naoki HAYASHI  Shigemasa TAKAI  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E104-A   No.2   pp.430-437
Publication Date: 2021/02/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.2020MAP0003
Type of Manuscript: Special Section PAPER (Special Section on Mathematical Systems Science and its Applications)
Category: 
Keyword: 
online convex optimization,  multi-agent systems,  event-triggered communication,  

Full Text: PDF>>
Buy this Article




Summary: 
This paper considers a distributed subgradient method for online optimization with event-triggered communication over multi-agent networks. At each step, each agent obtains a time-varying private convex cost function. To cooperatively minimize the global cost function, these agents need to communicate each other. The communication with neighbor agents is conducted by the event-triggered method that can reduce the number of communications. We demonstrate that the proposed online algorithm achieves a sublinear regret bound in a dynamic environment with slow dynamics.