Constructive approximations to the q=1/2 maximum entropy distribution from redundant and noisy data

Abstract

An approach adopted to consider the problem of constructing the q=1/2 maximum entropy distribution from redundant and noisy data was discussed. The advantage of this generalized approach, when dealing with very noisy data was illustrated by a numerical simulation. A strategy was proposed that evolved through different steps such as independent constraints were first preselected by recourse to a data independent technique. A backward approach was also proposed for reducing the parameters of such distributions. It was found that the sub-optimal strategies could be utilized in a broad range of situations.

Publication DOI: https://doi.org/10.1103/PhysRevE.70.021104
Divisions: College of Engineering & Physical Sciences > Mathematics
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: ©2004 American Physical Society
Uncontrolled Keywords: Physics and Astronomy(all),Condensed Matter Physics,Statistical and Nonlinear Physics,Mathematical Physics
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
https://journal ... sRevE.70.021104 (Publisher URL)
PURE Output Type: Article
Published Date: 2004-08-01
Authors: Rebollo-Neira, L. (ORCID Profile 0000-0002-7420-8977)
Plastino, A.

Download

[img]

Version: Accepted Version

| Preview

Export / Share Citation


Statistics

Additional statistics for this record