DCMA: yet another derandomization in covariance-matrix-adaptation.
Olivier TeytaudSylvain GellyPublished in: GECCO (2007)
Keyphrases
- covariance matrix
- covariance matrices
- principal component analysis
- sample size
- pseudo inverse
- gaussian mixture
- normal distribution
- positive definite
- multivariate gaussian
- mahalanobis distance
- geometrical interpretation
- correlation matrix
- eigendecomposition
- principal components
- eigenvalues and eigenvectors
- special case
- transformation matrix
- feature space