Ali H. Sayed

TL;DR: It is shown that in the small step-size regime, each agent in the network is able to achieve the same performance level as that of a centralized strategy corresponding to a fully connected network.

TL;DR: The analysis establishes that sub-gradient strategies can attain exponential convergence rates, as opposed to sub-linear rates, and that they can approach the optimal solution within O(p), for sufficiently small step-sizes, p.

TL;DR: This work presents a mathematical framework for overlapping multipath propagation over fading channels, which leads to developing a block least squares method for overlap multipath resolving, and presents a new approach for solving the problem of fast channel fading situations.

TL;DR: In this paper, the authors carried out a detailed transient analysis of the learning behavior of multi-agent networks, and revealed interesting results about the learning abilities of distributed strategies, including how combination policies influence the learning process of networked agents, and how these policies can steer the convergence point towards any of many possible Pareto optimal solutions.

TL;DR: In this article, it was shown that graph learning under partial observability is achievable for first-order vector autoregressive systems with a stable Laplacian combination matrix, when the network topology is drawn according to the Bollobas-Riordan model.