8 citations · 27 across the 45 of their papers we have counts for
5 papers · 1 filter
Distributed Unconstrained Optimization with Time-varying Cost Functions
Amir-Salar Esteki, Solmaz S. Kia
In this paper, we propose a novel solution for the distributed unconstrained optimization problem where the total cost is the summation of time-varying local cost functions of a gr…
Fast model averaging via buffered states and first-order accelerated optimization algorithms
Amir-Salar Esteki, Hossein Moradian, Solmaz S. Kia
In this letter, we study the problem of accelerating reaching average consensus over connected graphs in a discrete-time communication setting. Literature has shown that consensus…
Federated Learning Using Variance Reduced Stochastic Gradient for Probabilistically Activated Agents
M. R. Rostami, S. S. Kia
This paper proposes an algorithm for Federated Learning (FL) with a two-layer structure that achieves both variance reduction and a faster convergence rate to an optimal solution i…
The fastest linearly converging discrete-time average consensus using buffered information
Amir-Salar Esteki, Hossein Moradian, Solmaz S. Kia
In this letter, we study the problem of accelerating reaching average consensus over connected graphs in a discrete-time communication setting. Literature has shown that consensus…
Online Target Localization using Adaptive Belief Propagation in the HMM Framework
Min-Won Seo, Solmaz S. Kia
This paper proposes a novel adaptive sample space-based Viterbi algorithm for target localization in an online manner. The method relies on discretizing the target's motion space i…