rgpycrumbs.surfaces.gradient_imq

Classes

GradientIMQ

Gradient-enhanced Inverse Multi-Quadratic (IMQ) surface implementation.

Functions

negative_mll_imq_grad(log_params, x, y_flat, D_plus_1)
negative_mll_imq_map(log_params, init_eps, x, y_flat, ...)
_grad_imq_solve(x, y_full, noise_scalar, epsilon[, ...])
_grad_imq_predict(x_query, x_obs, alpha, epsilon)
_grad_imq_var(x_query, x_obs, K_inv, epsilon)

Module Contents

rgpycrumbs.surfaces.gradient_imq.negative_mll_imq_grad(log_params, x, y_flat, D_plus_1)

rgpycrumbs.surfaces.gradient_imq.negative_mll_imq_map(log_params, init_eps, x, y_flat, D_plus_1)

rgpycrumbs.surfaces.gradient_imq._grad_imq_solve(x, y_full, noise_scalar, epsilon, noise_per_obs=None)

rgpycrumbs.surfaces.gradient_imq._grad_imq_predict(x_query, x_obs, alpha, epsilon)

rgpycrumbs.surfaces.gradient_imq._grad_imq_var(x_query, x_obs, K_inv, epsilon)

class rgpycrumbs.surfaces.gradient_imq.GradientIMQ(x, y, gradients=None, smoothing=0.0001, length_scale=None, optimize=True, noise_per_obs=None, **_kwargs)

Bases: rgpycrumbs.surfaces._base.BaseGradientSurface

Gradient-enhanced Inverse Multi-Quadratic (IMQ) surface implementation.

Added in version 1.0.0.

_fit(smoothing, length_scale, optimize)

Internal method to perform parameter optimization.

_solve()

Internal method to solve the linear system for weights.

_predict_chunk(chunk)

Internal method for batch prediction.

_var_chunk(chunk)

Internal method for batch variance.