nnpiv.rkhs.RKHSIVL2CV

class nnpiv.rkhs.RKHSIVL2CV(kernel='rbf', gamma=2, degree=3, coef0=1, kernel_params=None, delta_scale='auto', delta_exp='auto', alpha_scales='auto', n_alphas=30, cv=6)[source]

RKHS IV estimator with L2 regularization and cross-validation.

Instrument projections are constructed from the positive eigenspaces of their Gram matrices. Candidate models and the final model retain the coefficient-space L2 normal equations.

Parameters

  • kernel (str or callable) – Kernel function or string identifier.

  • gamma (str or float) – Kernel coefficient passed to scikit-learn; for RBF, the kernel is exp(-gamma * ||x - x'||^2).

  • degree (int) – Degree for polynomial kernels.

  • coef0 (float) – Zero coefficient for polynomial kernels.

  • delta_scale (str or float) – Scale of the critical radius.

  • delta_exp (str or float) – Exponent of the critical radius.

  • alpha_scales (str or array-like) – Scale of the regularization parameter.

  • n_alphas (int) – Number of alpha scales to try.

  • cv (int) – Number of folds for cross-validation.

  • kernel_params (dict) – Additional parameters for the kernel.