Confidence region for distributed stochastic optimization problem via stochastic gradient tracking method
S Zhao, Y Liu - Automatica, 2024 - Elsevier
Since stochastic approximation (SA) based algorithms are easy to implement and need less
memory, they are very popular in distributed stochastic optimization problems. Many works …
memory, they are very popular in distributed stochastic optimization problems. Many works …
Asymptotic Properties of - Method with Diminishing Step-Size
S Zhao, Y Liu - IEEE Transactions on Automatic Control, 2023 - ieeexplore.ieee.org
The popular/push–pull method for distributed optimization problem may unify much of the
existing decentralized first-order methods based on gradient tracking technique. More …
existing decentralized first-order methods based on gradient tracking technique. More …