no code implementations • 24 Sep 2022 • Hesameddin Mohammadi, Meisam Razaviyayn, Mihailo R. Jovanović
Finally, by analyzing a class of accelerated gradient flow dynamics, whose suitable discretization yields the two-step momentum algorithm, we establish that stochastic performance tradeoffs also extend to continuous time.
no code implementations • 14 Mar 2021 • Hesameddin Mohammadi, Samantha Samuelson, Mihailo R. Jovanović
For convex quadratic problems, we employ tools from linear systems theory to show that transient growth arises from the presence of non-normal dynamics.
no code implementations • L4DC 2020 • Hesameddin Mohammadi, Mihailo R. Jovanovic', Mahdi Soltanolkotabi
Model-free reinforcement learning attempts to find an optimal control action for an unknown dynamical system by directly searching over the parameter space of controllers.
no code implementations • 26 Dec 2019 • Hesameddin Mohammadi, Armin Zare, Mahdi Soltanolkotabi, Mihailo R. Jovanović
Model-free reinforcement learning attempts to find an optimal control action for an unknown dynamical system by directly searching over the parameter space of controllers.
no code implementations • 27 May 2019 • Hesameddin Mohammadi, Meisam Razaviyayn, Mihailo R. Jovanović
We study the robustness of accelerated first-order algorithms to stochastic uncertainties in gradient evaluation.
no code implementations • 4 Jul 2018 • Armin Zare, Hesameddin Mohammadi, Neil K. Dhingra, Tryphon T. Georgiou, Mihailo R. Jovanović
Several problems in modeling and control of stochastically-driven dynamical systems can be cast as regularized semi-definite programs.