.png){kind=icon}
.png){kind=icon}
Return
The Gradient Tracking Is a Distributed Integral Action
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2023.3248487.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We revisit the recent gradient tracking algorithm for distributed consensus optimization from a control theoretic viewpoint. We show that the algorithm can be constructed by solving a servomechanism control problem stemming from the distributed implementation of a centralized gradient method. Moreover, we show that, if expressed in proper coordinates, the gradient tracking embeds an integral action fed by a signal related to the consensus error. Finally, we provide an alternative convergence analysis based on Lyapunov arguments that also proves exponential asymptotic stability of the optimal equilibrium.
Keywords:
Control for optimization
distributed optimization
gradient tracking
integral control
Journal
IF:
7
Papers:
1.3W
Citations:
6.7W