Provides utility to alter the learning rates when fitting a deepspat model
init_learn_rates(
sigma2y = 5e-04,
covfun = 0.01,
sigma2eta = 1e-04,
eta_mean = 0.1,
eta_mean2 = 0.1,
eta_sd = 0.1,
LFTpars = 0.01,
AFFpars = 0.01,
rho = 0.1,
vario = 0.1
)init_learn_rates returns a list with the learning rates. Call str(init_learn_rates()) to see the
structure of this list.
learning rate for the measurement-error variance
learning rate for the covariance-function (or matrix) parameters at the top layer
learning rate for the process variance
learning rate for the weight estimates or variational means
learning rate for the weight estimates or variational means
learning rate for the variational standard deviations (SDSP only)
learning rate for the parameters of the Mobius transformation
learning rate for the parameters of the affine transformation
learning rate for the correlation parameter in the multivariate model
learning rate for the parameter in the variogram