A perturbative approach to the reconstruction of the eigenvalue spectrum of a normal covariance matrix from a spherically truncated counterpart.
Filippo PalombiSimona TotiPublished in: J. Comput. Appl. Math. (2020)
Keyphrases
- covariance matrix
- covariance matrices
- principal component analysis
- mahalanobis distance
- sample size
- positive definite
- gaussian mixture
- eigendecomposition
- geometrical interpretation
- image reconstruction
- eigenvalues and eigenvectors
- pseudo inverse
- cma es
- symmetric matrix
- correlation matrix
- transformation matrix
- principal components
- objective function
- feature extraction
- computer vision