Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold
This paper proposes a class of covariance estimators based on information divergences in heterogeneous environments. In particular, the problem of covariance estimation is reformulated on the Riemannian manifold of Hermitian positive-definite (HPD) matrices. The means associated with information div...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-03-01
|
Series: | Entropy |
Subjects: | |
Online Access: | http://www.mdpi.com/1099-4300/20/4/219 |
id |
doaj-c9c8030879fb4d7da9dcae24b4c837f6 |
---|---|
record_format |
Article |
spelling |
doaj-c9c8030879fb4d7da9dcae24b4c837f62020-11-24T21:28:37ZengMDPI AGEntropy1099-43002018-03-0120421910.3390/e20040219e20040219Robust Covariance Estimators Based on Information Divergences and Riemannian ManifoldXiaoqiang Hua0Yongqiang Cheng1Hongqiang Wang2Yuliang Qin3School of Electronic Science, National University of Defence Technology, Changsha 410073, ChinaSchool of Electronic Science, National University of Defence Technology, Changsha 410073, ChinaSchool of Electronic Science, National University of Defence Technology, Changsha 410073, ChinaSchool of Electronic Science, National University of Defence Technology, Changsha 410073, ChinaThis paper proposes a class of covariance estimators based on information divergences in heterogeneous environments. In particular, the problem of covariance estimation is reformulated on the Riemannian manifold of Hermitian positive-definite (HPD) matrices. The means associated with information divergences are derived and used as the estimators. Without resorting to the complete knowledge of the probability distribution of the sample data, the geometry of the Riemannian manifold of HPD matrices is considered in mean estimators. Moreover, the robustness of mean estimators is analyzed using the influence function. Simulation results indicate the robustness and superiority of an adaptive normalized matched filter with our proposed estimators compared with the existing alternatives.http://www.mdpi.com/1099-4300/20/4/219information divergenceRiemannian manifoldcovariance estimationmean estimatorheterogeneous clutter |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaoqiang Hua Yongqiang Cheng Hongqiang Wang Yuliang Qin |
spellingShingle |
Xiaoqiang Hua Yongqiang Cheng Hongqiang Wang Yuliang Qin Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold Entropy information divergence Riemannian manifold covariance estimation mean estimator heterogeneous clutter |
author_facet |
Xiaoqiang Hua Yongqiang Cheng Hongqiang Wang Yuliang Qin |
author_sort |
Xiaoqiang Hua |
title |
Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold |
title_short |
Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold |
title_full |
Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold |
title_fullStr |
Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold |
title_full_unstemmed |
Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold |
title_sort |
robust covariance estimators based on information divergences and riemannian manifold |
publisher |
MDPI AG |
series |
Entropy |
issn |
1099-4300 |
publishDate |
2018-03-01 |
description |
This paper proposes a class of covariance estimators based on information divergences in heterogeneous environments. In particular, the problem of covariance estimation is reformulated on the Riemannian manifold of Hermitian positive-definite (HPD) matrices. The means associated with information divergences are derived and used as the estimators. Without resorting to the complete knowledge of the probability distribution of the sample data, the geometry of the Riemannian manifold of HPD matrices is considered in mean estimators. Moreover, the robustness of mean estimators is analyzed using the influence function. Simulation results indicate the robustness and superiority of an adaptive normalized matched filter with our proposed estimators compared with the existing alternatives. |
topic |
information divergence Riemannian manifold covariance estimation mean estimator heterogeneous clutter |
url |
http://www.mdpi.com/1099-4300/20/4/219 |
work_keys_str_mv |
AT xiaoqianghua robustcovarianceestimatorsbasedoninformationdivergencesandriemannianmanifold AT yongqiangcheng robustcovarianceestimatorsbasedoninformationdivergencesandriemannianmanifold AT hongqiangwang robustcovarianceestimatorsbasedoninformationdivergencesandriemannianmanifold AT yuliangqin robustcovarianceestimatorsbasedoninformationdivergencesandriemannianmanifold |
_version_ |
1725969425618698240 |