Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Mohammadi, Hesameddin"'
We study momentum-based first-order optimization algorithms in which the iterations utilize information from the two previous steps and are subject to an additive white noise. This setup uses noise to account for uncertainty in either gradient evalua
Externí odkaz:
http://arxiv.org/abs/2209.11920
Optimization algorithms are increasingly being used in applications with limited time budgets. In many real-time and embedded scenarios, only a few iterations can be performed and traditional convergence metrics cannot be used to evaluate performance
Externí odkaz:
http://arxiv.org/abs/2103.08017
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. The convergence behavior and statistical properties of these approaches are of
Externí odkaz:
http://arxiv.org/abs/1912.11899
We study the robustness of accelerated first-order algorithms to stochastic uncertainties in gradient evaluation. Specifically, for unconstrained, smooth, strongly convex optimization problems, we examine the mean-squared error in the optimization va
Externí odkaz:
http://arxiv.org/abs/1905.11011
Autor:
Mohammadi, Hesameddin, Zeidler, Anita, Youngman, Randall E., Fischer, Henry E., Salmon, Philip S.
Publikováno v:
Journal of Chemical Physics; 2/14/2024, Vol. 160 Issue 6, p1-18, 18p
Autor:
Zare, Armin, Mohammadi, Hesameddin, Dhingra, Neil K., Georgiou, Tryphon T., Jovanović, Mihailo R.
Several problems in modeling and control of stochastically-driven dynamical systems can be cast as regularized semi-definite programs. We examine two such representative problems and show that they can be formulated in a similar manner. The first, in
Externí odkaz:
http://arxiv.org/abs/1807.01739
In this paper, we propose an iterative method for using SOS programming to estimate the region of attraction of a polynomial vector field, the conjectured convergence of which necessitates the existence of polynomial Lyapunov functions whose sublevel
Externí odkaz:
http://arxiv.org/abs/1704.06983
Autor:
Mendes Da Silva, Rita, Zeidler, Anita, Mohammadi, Hesameddin, Gammond, Lawrence V. D., Girón Lange, Esther, Youngman, Randall E., Aitken, Bruce G., Hannon, Alex C., Benmore, Chris J., Vaughan, Gavin B. M., Salmon, Philip S.
Publikováno v:
Journal of Chemical Physics; 8/14/2023, Vol. 159 Issue 6, p1-16, 16p
In this paper, we present a branch and bound algorithm for extracting approximate solutions to Global Polynomial Optimization (GPO) problems with bounded feasible sets. The algorithm is based on a combination of SOS/Moment relaxations and successivel
Externí odkaz:
http://arxiv.org/abs/1609.01019
Autor:
Bakhshian Nik, Amirala, Zare, Hossein, Razavi, Seyedsahameddin, Mohammadi, Hesameddin, Torab Ahmadi, Pooya, Yazdani, Narges, Bayandori, Mehrdad, Rabiee, Navid, Izadi Mobarakeh, Jalal
Publikováno v:
In Microporous and Mesoporous Materials June 2020 299