rocsvm.solve {rocsvm.path} | R Documentation |
Computes the Lagrangian multipliers(alpha
), which are solutions of ROC-SVM using Quadratic Programming.
rocsvm.solve(K, lambda, rho = 1, eps = 1e-08)
K |
The kernelized matrix, i.e., K< .,. >. |
lambda |
The regularization parameter that users want in ROC-SVM model. |
rho |
A positive constant (default : 1) |
eps |
Adjustment computing errors (default : 1e-08) |
Seung Jun Shin, Do Hyun Kim
n <- 30 p <- 2 delta <- 1 set.seed(309) y <- c(rep(1, n/2), rep(-1, n/2)) x <- matrix(0, n, p) for (i in 1:n){ if (y[i] == 1) { x[i,] <- rnorm(p, -delta, 1) } else { x[i,] <- rnorm(p, delta, 1) } } K <- radial.kernel(x,x) rocsvm.solve(K, lambda = 1, rho = 1)