15 citations · 31 across the 13 of their papers we have counts for
7 papers · 1 filter
On the Stability of Power Systems with AI Data Centers: A Multi-Equilibrium Switched DAE Framework
Vishal Shenoy, Damola Ajeyemi, Mahmoud Abdelgalil +3
The rapid growth of Artificial Intelligence (AI) data centers is introducing dynamic loads into power transmission systems as GPU clusters switch between computational phases with…
The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning
Michael Tang, Mahmoud Abdelgalil, Jorge I. Poveda
Randomized exploration is central to bandit learning, multi-agent reinforcement learning, and zeroth-order policy search, yet its independence and privacy are usually only treated…
Stochastic Lie-Bracket Approximations for Zeroth-Order Optimization on Manifolds
Mahmoud Abdelgalil, Miroslav Krstic, Jorge I. Poveda
We propose a continuous-time algorithm for zeroth-order global optimization of smooth functions on compact manifolds that synthesizes Riemannian gradient dynamics using only object…
Non-Holonomic Gradient Play: Leafwise Nash Equilibria, Stability, and Deception
Mahmoud Abdelgalil, Miroslav Krstic, Jorge I. Poveda
We study generalized learning dynamics in multi-agent systems whose joint state evolves on a manifold and whose agents act through state-dependent, potentially nonholonomic vector…
A Ballantine-Type Factorization of Diffeomorphisms
Mahmoud Abdelgalil, Tryphon T. Georgiou
We show that on a compact, connected, Riemannian manifold without boundary, every isotopic to the identity diffeomorphism can be written as a finite composition of optimal mass tra…
The Holonomy of Optimal Mass Transport: The Smooth Case
Mahmoud Abdelgalil, Tryphon T. Georgiou
We prove that, on a smooth manifold equipped with a constant rank horizontal distribution and a smooth inner product on , any horizontal vector field can be writte…
On the Isospectral Nature of Minimum-Shear Covariance Control
Ralph Sabbagh, Asmaa Eldesoukey, Mahmoud Abdelgalil +1
We revisit Brockett's attention in the context of bilinear gradient flow of an ensemble, and explore an alternative formalism that aims to reduce shear by minimizing the conditioni…