Dynamics of differential entropy maximization process via the Speed Gradient principle

Author

Shalymov, Dmitry S. ; Fradkov, Alexander L.

Author_Institution

Math. & Mech. Fac., St. Petersburg State Univ., St. Petersburg, Russia

fYear

2015

fDate

16-19 June 2015

Firstpage

434

Lastpage

441

Abstract

Dynamics of non-stationary processes that follow the MaxEnt principle for differential entropy is considered. A set of equations describing the dynamics of probability density function (pdf) for such processes is proposed. Equations are derived based on the Speed-Gradient principle originated in the control theory. The uniqueness of the limit pdf and asymptotic convergence of pdf are examined under the mass and energy conservation constraints.

Keywords

gradient methods; maximum entropy methods; optimisation; probability; MaxEnt principle; asymptotic convergence; control theory; differential entropy maximization process; energy conservation constraint; mass conservation constraint; nonstationary process; probability density function; speed gradient principle; speed-gradient principle; Convergence; Entropy; Mathematical model; Probability density function; Random variables; Uncertainty; Differential entropy; maximum entropy (Max-Ent) principle; non-stationary processes; probability density function (pdf); speed-gradient principle;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Automation (MED), 2015 23th Mediterranean Conference on

Conference_Location

Torremolinos

Type

conf

DOI

10.1109/MED.2015.7158787

Filename

7158787