lm_gradient_cv: Cross validation for Linear Models with gradient

In vincnardelli/gradient: Gradient

Description

lm_gradient_cv is used to perform a k-fold cross validation to a linear model with gradient or steepest descent.

Usage

lm_gradient_cv(
  n.folds,
  b,
  formula,
  data = NULL,
  maxit = 1000,
  tolerance = 1e-05,
  stepsize = 1e-04,
  fun = "sd",
  parallel = FALSE
)

Arguments

n.folds	number of folds (k)
b	initial values for beta
formula	an object of class "formula" (or one that can be coerced to that class): a symbolic description of the model to be fitted
data	an optional data frame, list or environment. If not found in data, the variables are taken from environment(formula)
maxit	number of max iterations of the algorithm
tolerance	the algorithm will stop if tolerance is reached
stepsize	size of each step (only for gradient descent)
fun	function can be sd for steepest descent or gd for gradient descent
parallel	perform the cross validation in multi-core

Value

the function returns an object of class "gradient"

vincnardelli/gradient documentation built on July 30, 2020, 9:57 a.m.