arXiv subjects

Amir Mehrnoosh

Publications and source records attributed to Amir Mehrnoosh.

3 recordsLinked to original sources

arXiv2026

Model-Free Aggregative Cooperative Optimization via Randomized Gradient-Free Minimization and Exploration Momentum

Aggregative cooperative optimization problems arise in distributed decision-making settings where each agent's objective depends on its own decision as well as on an aggregate variable capturing global system behavior. Motivated by practical scenarios where gradient information is unavailable, this paper introduces a randomized gradient-free algorithm, named ARGFree, for solving such problems. ARGFree combines finite-difference gradient approximations with a set of tracking variables, emulating the behavior of a gradient-based method. We prove that ARGFree converges in expectation to an approximate optimizer, with the approximation error stemming from the use of a randomized gradient estimator. To enhance performance in high-dimensional settings, we further propose an improved variant, ARGFree-EM, which incorporates momentum in the exploration signals to smooth sudden fluctuations in the gradient exploration signals and thereby improve the accuracy of the underlying distributed tracking mechanism. To the best of our knowledge, the class of ARGFree methods is the first in the literature capable of solving aggregating cooperative optimization problems without gradient information.

math.OC↗

arXiv2025

Two-point Random Gradient-free Methods for Model-free Feedback Optimization

Feedback optimization has emerged as a promising approach for optimizing the steady-state operation of dynamical systems while requiring minimal modeling efforts. Unfortunately, most existing feedback optimization methods rely on knowledge of the plant dynamics, which may be difficult to obtain or estimate in practice. In this paper, we introduce a novel randomized two-point gradient-free feedback optimization method, inspired by zeroth-order optimization techniques. Our method relies on function evaluations at two points to estimate the gradient and update the control input in real-time. We provide convergence guarantees and show that our method is capable of computing an $ε$-stationary point for smooth, nonconvex functions at a rate $\mathcal{O} (ε^{-1})$, in line with existing results for two-point gradient-free methods for static optimization. Simulation results validate the findings.

math.OC↗

arXiv2025

Optimization of Linear Multi-Agent Dynamical Systems via Feedback Distributed Gradient Descent Methods

Feedback optimization is an increasingly popular control paradigm to optimize dynamical systems, accounting for control objectives that concern the system operation at steady-state. Existing feedback optimization techniques heavily rely on centralized systems and controller architectures, and thus suffer from scalability and privacy issues when systems become large-scale. In this paper, we propose a distributed architecture for feedback optimization inspired by distributed gradient descent, whereby each agent updates its local control variable by combining the average of its neighbors with a local negative gradient step. Under convexity and smoothness assumptions for the cost, we establish convergence of the control method to a critical optimization point. By reinforcing the assumptions to restricted strong convexity, we show that our algorithm converges linearly to a neighborhood of the optimal point, where the size of the neighborhood depends on the choice of the stepsize. Simulations corroborate the theoretical results.

math.OC↗