Natural gradient algorithm for stochastic distribution systems with output feedback
نویسندگان
چکیده
منابع مشابه
A Natural Gradient Algorithm for Stochastic Distribution Systems
In this paper, we propose a steepest descent algorithm based on the natural gradient to design the controller of an open-loop stochastic distribution control system (SDCS) of multi-input and single output with a stochastic noise. Since the control input vector decides the shape of the output probability density function (PDF), the purpose of the controller design is to select a proper control i...
متن کاملStochastic Information Gradient Algorithm with Generalized Gaussian Distribution Model
This paper presents a parameterized version of the stochastic information gradient (SIG) algorithm, in which the error distribution is modeled by generalized Gaussian density (GGD), with location, shape, and dispersion parameters. Compared with the kernel-based SIG (SIGKernel) algorithm, the GGD-based SIG (SIG-GGD) algorithm does not involve kernel width selection. If the error is zero-mean, th...
متن کاملRobust Static Output Feedback Control for Stochastic Hybrid Systems
This paper deals with the stabilization problem for a class of uncertain stochastic systems with Markovian jumps via the static output feedback control, where the uncertain parameters are norm bounded. A static output feedback controller that makes the closed-loop systems asymptotically mean-square stable is designed, which is obtained by solving some linear matrix inequalities.
متن کاملImproving Stochastic Gradient Descent with Feedback
In this paper we propose a simple and efficient method for improving stochastic gradient descent methods by using feedback from the objective function. The method tracks the relative changes in the objective function with a running average, and uses it to adaptively tune the learning rate in stochastic gradient descent. We specifically apply this idea to modify Adam, a popular algorithm for tra...
متن کاملOutput-feedback stochastic nonlinear stabilization
We present the rst result on global output-feedback stabilization (in probability) for stochastic nonlinear continuous-time systems. The class of systems that we consider is a stochastic counterpart of the broadest class of deterministic systems for which globally stabilizing controllers are currently available. Our controllers are \inverse optimal" and possess an innnite gain margin. A reader ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Differential Geometry and its Applications
سال: 2013
ISSN: 0926-2245
DOI: 10.1016/j.difgeo.2013.07.004