1 citations · 1 across the 7 of their papers we have counts for
8 papers
Scalar Communication via Random Direction Refreshing for Distributed Optimization
Mohammadreza Rostami, Solmaz S. Kia
Distributed optimization over networks requires agents to repeatedly exchange decision variables with their neighbors. When the decision dimension is large, these exchanges dom…
Adaptive Threshold-Driven Continuous Greedy Method for Scalable Submodular Optimization
Mohammadreza Rostami, Solmaz S. Kia
Submodular maximization under matroid constraints is a fundamental problem in combinatorial optimization with applications in sensing, data summarization, active learning, and reso…
Scalar Federated Learning for Linear Quadratic Regulator
Mohammadreza Rostami, Shahriar Talebi, Solmaz S. Kia
We propose ScalarFedLQR, a communication-efficient federated algorithm for model-free learning of a common policy in linear quadratic regulator (LQR) control of cooperative agents.…
FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative
Mohammadreza Rostami, Solmaz S. Kia
This paper introduces \texttt{FedMPDD} (\textbf{Fed}erated Learning via \textbf{M}ulti-\textbf{P}rojected \textbf{D}irectional \textbf{D}erivatives), a novel algorithm that simulta…
Time-Varying Convex Optimization with Computational Complexity
M. Rostami, S. S. Kia
In this article, we consider the problem of unconstrained time-varying convex optimization, where the cost function changes with time. We provide an in-depth technical analysis of…
FedScalar: Federated Learning with Scalar Communication for Bandwidth-Constrained Networks
M. Rostami, S. S. Kia
In bandwidth-constrained federated learning~(FL) settings, the repeated upload of high-dimensional model updates from agents to a central server constitutes the primary bottleneck,…
Projected Forward Gradient-Guided Frank-Wolfe Algorithm via Variance Reduction
M. Rostami, S. S. Kia
This paper aims to enhance the use of the Frank-Wolfe (FW) algorithm for training deep neural networks. Similar to any gradient-based optimization algorithm, FW suffers from high c…
First-Order Dynamic Optimization for Streaming Convex Costs
M. Rostami, H. Moradian, S. S. Kia
This paper proposes a set of novel optimization algorithms for solving a class of convex optimization problems with time-varying streaming cost function. We develop an approach to…