On Decentralized Tracking with ADMM for Problems with Time-Varying Curvature
Optimization and Control
2019-03-18 v1
Abstract
We analyze the performance of the alternating direction method of multipliers (ADMM) to track, in a decentralized manner, a solution of a stochastic sequence of optimization problems parametrized by a discrete time Markov process. The main advantage of considering a stochastic model is that we allow the objective functions to occasionally lose strong convexity and/or Lipschitz continuity of their gradients. Due to the stochastic nature of our model, the tracking statement is given in a mean square deviation error.
Cite
@article{arxiv.1903.06492,
title = {On Decentralized Tracking with ADMM for Problems with Time-Varying Curvature},
author = {Marie Maros and Joakim Jalén},
journal= {arXiv preprint arXiv:1903.06492},
year = {2019}
}
Comments
Extended version of CDC submission