Relation between PLS and OLS regression in terms of the eigenvalue distribution of the regressor covariance matrix.
David del ValJosé R. BerrenderoAlberto SuárezPublished in: CoRR (2023)
Keyphrases
- covariance matrix
- normal distribution
- partial least squares
- covariance matrices
- principal component analysis
- sample size
- regression method
- regression model
- gaussian mixture
- geometrical interpretation
- symmetric matrix
- eigenvalues and eigenvectors
- multivariate gaussian
- estimation error
- pseudo inverse
- probability distribution
- eigendecomposition
- principal components
- dimension reduction
- random variables
- mahalanobis distance
- neural network
- mahalanobis metric