wavy.GPfcts
Module Contents
Functions
|
Isotropic squared exponential kernel. Computes |
|
Computes statistics of the GP posterior predictive distribution |
|
Returns a function that computes the negative log marginal |
- wavy.GPfcts.kernel(X1, X2, l=1.0, sigma_f=1.0)
Isotropic squared exponential kernel. Computes a covariance matrix from points in X1 and X2. Args:
X1: Array of m points (m x d). X2: Array of n points (n x d).
- Returns:
Covariance matrix (m x n).
- wavy.GPfcts.posterior_predictive_nigp(X_s, X_train, Y_train, l=None, sigma_f=None, sigma_y=None, sigma_x=None, Grad_fmean=None)
Computes statistics of the GP posterior predictive distribution from m training data X_train and Y_train and n new inputs X_s. Args:
X_s: New input locations (n x d) X_train: Training locations (m x d) Y_train: Training targets (m x 1) l: length scale parameter sigma_f: signal variance parameter sigma_y: noise paramter on y sigma_x: noise parameter on x
- Returns:
Posterior mean vector (n x d) and covariance matrix (n x n)
- wavy.GPfcts.nll_fn_nigp(X_train, Y_train, Grad_fmean, naive=False)
Returns a function that computes the negative log marginal likelihood for training data X_train and Y_train and given noise level. Args:
X_train: training locations (m x d). Y_train: training targets (m x 1). noise: known noise level of Y_train. naive: if True use a naive implementation of Eq. (7), if
False use a numerically more stable implementation.
- Returns:
Minimization objective.