Implementation of Kernel Partial Least Squares (Kernel PLS) [1], a nonlinear extension of Partial Least Squares regression based on Reproducing Kernel Hilbert Spaces (RKHS).
Kernel PLS allows modeling nonlinear relationships by applying the kernel trick to the standard PLS framework, enabling latent component extraction in feature space without explicit computation of the mapping.
Proposed functionality
- Support for common kernel functions (e.g., RBF, polynomial, linear)
- Ability to tune kernel hyperparameters (e.g., gamma, degree)
- Consistent API for fit / transform / predict
Reference
[1] Rosipal, R., & Trejo, L. J. (2001).
Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space.
Journal of Machine Learning Research, 2, 97–123.
Implementation of Kernel Partial Least Squares (Kernel PLS) [1], a nonlinear extension of Partial Least Squares regression based on Reproducing Kernel Hilbert Spaces (RKHS).
Kernel PLS allows modeling nonlinear relationships by applying the kernel trick to the standard PLS framework, enabling latent component extraction in feature space without explicit computation of the mapping.
Proposed functionality
Reference
[1] Rosipal, R., & Trejo, L. J. (2001).
Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space.
Journal of Machine Learning Research, 2, 97–123.