Learn R Programming
rlibkriging (version 1.2-3)

fit.WarpKriging: Fit a WarpKriging model to data

Description

(Re-)fit an already-constructed WarpKriging object on new data. The warping specification and kernel are kept from construction.

Usage

# S3 method for WarpKriging
fit(
  object,
  y,
  X,
  regmodel = "constant",
  normalize = FALSE,
  optim = "BFGS+Adam",
  objective = "LL",
  parameters = NULL,
  noise = NULL,
  ...
)

Value

No return value. WarpKriging object argument is modified.

Arguments

object

WarpKriging object (created with the constructor or an empty-kernel call)

y

numeric vector of observations (n)

X

numeric matrix of inputs (n x d)

regmodel

trend: "constant", "linear", "quadratic"

normalize

logical; normalise continuous inputs?

optim

optimiser; "none" keeps the values from parameters

objective

"LL" (log-likelihood)

parameters

optional named list of initial hyper-parameter values (theta, warp_params, noise) and/or optimiser knobs (adam_lr, max_iter_adam, max_iter_bfgs). See WarpKriging.

noise

numeric vector of per-observation noise variances (length n), or NULL (default) for noise-free interpolation.

...

ignored