High dimensional covariance matrix estimation by penalizing the matrix-logarithm transformed likelihood.
Philip L. H. YuXiaohang WangYuanyuan ZhuPublished in: Comput. Stat. Data Anal. (2017)
Keyphrases
- covariance matrix
- high dimensional
- estimation error
- covariance matrices
- positive definite
- eigenvalues and eigenvectors
- principal component analysis
- pseudo inverse
- eigendecomposition
- correlation matrix
- sample size
- symmetric matrix
- geometrical interpretation
- gaussian mixture
- low dimensional
- dimensionality reduction
- similarity search
- transformation matrix
- maximum likelihood
- mahalanobis distance
- multivariate gaussian
- data points
- cma es
- machine learning
- class conditional densities
- high dimensional data
- objective function
- computer vision