Adaptive M-Estimators For Robust Covariance Estimation
نویسندگان
چکیده
Robust covariance estimates are required in many applications. Here, a promising adaptive robust scale estimator is extended to this problem and compared to other robust estimators. Often the performance analysis of covariance estimators is performed from the perspective of the final application. However, different applications have different requirements, hence we make a comparison based on some general metrics. Results show that the adaptive scheme shows good performance under the nominal case and graceful degradation in performance with increasing levels of contamination.
منابع مشابه
Adaptive RBF network control for robot manipulators
TThe uncertainty estimation and compensation are challenging problems for the robust control of robot manipulators which are complex systems. This paper presents a novel decentralized model-free robust controller for electrically driven robot manipulators. As a novelty, the proposed controller employs a simple Gaussian Radial-Basis-Function Network as an uncertainty estimator. The proposed netw...
متن کاملA Two-Phase Robust Estimation of Process Dispersion Using M-estimator
Parameter estimation is the first step in constructing any control chart. Most estimators of mean and dispersion are sensitive to the presence of outliers. The data may be contaminated by outliers either locally or globally. The exciting robust estimators deal only with global contamination. In this paper a robust estimator for dispersion is proposed to reduce the effect of local contamination ...
متن کاملRobust 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 divergences are derived and used as the estimators. Without resorting to the complete knowledge of t...
متن کاملAn adaptive method for combined covariance estimation and classification
In this paper a family of adaptive covariance estimators is proposed to mitigate the problem of limited training samples for application to hyperspectral data analysis in quadratic maximum likelihood classification. These estimators are the combination of adaptive classification procedures and regularized covariance estimators. In these proposed estimators, the semi-labeled samples (whose label...
متن کاملAdaptive Thresholding for Sparse Covariance Matrix Estimation
In this article we consider estimation of sparse covariance matrices and propose a thresholding procedure that is adaptive to the variability of individual entries. The estimators are fully data-driven and demonstrate excellent performance both theoretically and numerically. It is shown that the estimators adaptively achieve the optimal rate of convergence over a large class of sparse covarianc...
متن کامل