epspath function

Fit the entire epsilon path for Support Vector Regression

The Suport Vector Regression (SVR) employs epsilon-intensive loss which ignores errors smaller than epsilon. This algorithm computes the entire paths for SVR solution as a function of epsilon at a given regularization parameter lambda, which we call epsilon path.

epspath(x, y, lambda = 1, kernel.function = radial.kernel,
  param.kernel = 1, ridge = 1e-08, eps = 1e-07, eps.min = 1e-08, ...)

Arguments

• x: The data matrix (n x p) with n rows (observations) on p variables (columns)
• y: The real number valued response variable
• lambda: The regularization parameter value.
• kernel.function: User defined kernel function. See svmpath.
• param.kernel: Parameter(s) of the kernels. See svmpath.
• ridge: Sometimes the algorithm encounters singularities; in this case a small value of ridge can help, default is ridge = 1e-8
• eps: A small machine number which is used to identify minimal step sizes
• eps.min: The smallest value of epsilon for termination of the algorithm. Default is eps.min = 1e-8
• ...: Generic compatibility

Returns

An 'epspath' object is returned.

Examples

set.seed(1)
n <- 30
p <- 50

x <- matrix(rnorm(n*p), n, p)
e <- rnorm(n, 0, 1)
beta <- c(1, 1, rep(0, p-2))
y <- x %*% beta + e
lambda <- 1
eobj <- epspath(x, y, lambda = lambda)

See Also

predict.epspath, plot.epspath, svrpath

Author(s)

Do Hyun Kim, Seung Jun Shin