A New Method to Solve Singularity Problems in Covariance Matrices
نویسندگان
چکیده
Due to the dependency structure, most of the covariance matrix faces with the singularity problem. There are several methods to overcome this challenge. The most well-known ones are the eigen-value, singular value, and cholesky decompositions. In this paper, we develop a new method to deal with the singularity problem while preserving the covariance structure of the original matrix and compare our alternative solution with other methods. For analysis we generate various covariance matrices that have different dimensions and dependency structures and compare the CPU times of each approach.
منابع مشابه
A New Quadratic Classifier Applied to Biometric Recognition
In biometric recognition applications, the number of training examples per class is limited and consequently the conventional quadratic classifier either performs poorly or cannot be calculated. Other non-conventional quadratic classifiers have been used in limited sample and high dimensional classification problems. In this paper, a new quadratic classifier called Maximum Entropy Covariance Se...
متن کاملVisual Analysis of the Use of Mixture Covariance Matrices in Face Recognition
The quadratic discriminant (QD) classifier has proved to be simple and effective in many pattern recognition problems. However, it requires the computation of the inverse of the sample group covariance matrix. In many biometric problems, such as face recognition, the number of training patterns is considerably smaller than the number of features, and therefore the covariance matrix is singular....
متن کاملSolution of Harmonic Problems with Weak Singularities Using Equilibrated Basis Functions in Finite Element Method
In this paper, Equilibrated Singular Basis Functions (EqSBFs) are implemented in the framework of the Finite Element Method (FEM), which can approximately satisfy the harmonic PDE in homogeneous and heterogeneous media. EqSBFs are able to automatically reproduce the terms consistent with the singularity order in the vicinity of the singular point. The newly made bases are used as the compliment...
متن کاملNew Methods for Handling Singular Sample Covariance Matrices
The estimation of a covariance matrix from an insufficient amount of data is one of the most common problems in fields as diverse as multivariate statistics, wireless communications, signal processing, biology, learning theory and finance. In a joint work of Marzetta, Tucci and Simon, a new approach to handle singular covariance matrices was suggested. The main idea was to use dimensionality re...
متن کاملEstimating Tree-Structured Covariance Matrices via Mixed-Integer Programming
We present a novel method for estimating tree-structured covariance matrices directly from observed continuous data. Specifically, we estimate a covariance matrix from observations of p continuous random variables encoding a stochastic process over a tree with p leaves. A representation of these classes of matrices as linear combinations of rank-one matrices indicating object partitions is used...
متن کامل