A natural gradient algorithm for stochastic distribution systems

DOI10.3390/E16084338MaRDI QIDQ296299zbMATH OpenOpenAlexFDO

Authors Zhenning Zhang, Lin Jiu, Huafei Sun, Linyu Peng

Publication date 15 June 2016

Published in Entropy (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3390/e16084338

zbMATH Keywords

Kullback-Leibler divergencenatural gradient algorithmstochastic distribution control system

Mathematics Subject Classification ID

Parametric inference (62F99) Stochastic systems in control theory (general) (93E03) Measures of information, entropy (94A17)

Review text

Summary: 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 input vector, so that the output PDF of the SDCS can be as close as possible to the target PDF. In virtue of the statistical characterizations of the SDCS, a new framework based on a statistical manifold is proposed to formulate the control design of the input and output SDCSs. Here, the Kullback-Leibler divergence is presented as a cost function to measure the distance between the output PDF and the target PDF. Therefore, an iterative descent algorithm is provided, and the convergence of the algorithm is discussed, followed by an illustrative example of the effectiveness.

Recommendations

• Natural gradient algorithm for stochastic distribution systems with output feedback
• Principal whitened gradient-projection algorithm for distributions control
• Model reference adaptive control of the output stochastic distributions for unknown linear stochastic systems
• Stochastic distribution control system design. A convex optimization approach.
• An information geometry algorithm for distribution control

Cites work

• An information geometry algorithm for distribution control
• Defining the curvature of a statistical problem (with applications to second order efficiency)
• Differential geometry of a parametric family of invertible linear systems—Riemannian metric, dual affine connections, and divergence
• scientific article; zbMATH DE number 1560711 (Why is no real title available?)
• Information geometric characterization of the complexity of fractional Brownian motions
• Iterative approximation of statistical distributions and relation to information geometry
• Minimum entropy filtering for multivariate stochastic systems with non-Gaussian noises
• Natural gradient algorithm for stochastic distribution systems with output feedback
• Stochastic distribution control system design. A convex optimization approach.
• The geometric structures and instability of entropic dynamical models
• The geometry of exponential families

Cited in

(3)

• Natural gradient algorithm for stochastic distribution systems with output feedback
• An information geometry algorithm for distribution control
• Principal whitened gradient-projection algorithm for distributions control

This page was built for publication: A natural gradient algorithm for stochastic distribution systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q296299)