Imperial College London
Portrait Picture

ProfessorEmmaMcCoy

Faculty of Natural Sciences, Department of Mathematics

Academic Visitor
 
 
 
//

Contact

 

e.mccoy

 
 
//

Assistant

 

Ms Gemma Sutcliffe +44 (0)20 7594 8807

 
//

Location

 

4.09Faculty BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Yang:2011:10.1016/j.sigpro.2010.09.004,
author = {Yang, Z and Walden, AT and McCoy, EJ},
doi = {10.1016/j.sigpro.2010.09.004},
journal = {Signal Processing},
pages = {864--876},
title = {Correntropy: Implications of nonGaussianity for the moment expansion and deconvolution},
url = {http://dx.doi.org/10.1016/j.sigpro.2010.09.004},
volume = {91},
year = {2011}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The recently introduced correntropy function is an interesting and useful similarity measure between two random variables which has found myriad applications in signal processing. A series expansion for correntropy in terms of higher-order moments of the difference between the two random variables has been used to try to explain its statistical properties for uses such as deconvolution. We examine the existence and form of this expansion, showing that it may be divergent, e.g., when the difference has the Laplace distribution, and give sufficient conditions for its existence for differently characterized sub-Gaussian distributions. The contribution of the higher-order moments can be quite surprising, depending on the size of the Gaussian kernel in the definition of the correntropy. In the blind deconvolution setting we demonstrate that statistical exchangeability explains the existence of sub-optimal minima in the correntropy cost surface and show how the positions of these minima are controlled by the size of the Gaussian kernel.
AU  - Yang,Z
AU  - Walden,AT
AU  - McCoy,EJ
DO  - 10.1016/j.sigpro.2010.09.004
EP  - 876
PY  - 2011///
SP  - 864
TI  - Correntropy: Implications of nonGaussianity for the moment expansion and deconvolution
T2  - Signal Processing
UR  - http://dx.doi.org/10.1016/j.sigpro.2010.09.004
UR  - http://hdl.handle.net/10044/1/6853
VL  - 91
ER  -
Download