Module kernel 

Kernel functions equivalent to LIBSVM’s linear, polynomial, RBF, sigmoid, and precomputed kernels. Kernel functions matching the original LIBSVM.

Provides both:

• Standalone k_function for prediction (operates on sparse node slices)
• Kernel struct for training (precomputes x_square for RBF, stores refs)

Structs

Kernel

Kernel evaluator for training. Holds references to the dataset and precomputes x_square[i] = dot(x[i], x[i]) for RBF kernels.

Functions

dot

Sparse dot product of two sorted-by-index node slices.

k_function

Evaluate the kernel function K(x, y) for the given parameters.

powi

Integer power by squaring. Matches LIBSVM’s powi(base, times).