Check_KKT: Check on the condition of Karush-Kuhn-Tucker

In penalizedcdf: Estimate a Penalized Linear Model using the CDF Penalty Function

Check on the condition of Karush-Kuhn-Tucker

Description

Control over Karush-Kuhn-Tucker (Karush, 1939) conditions for the estimates obtained.

Usage

check_KKT(obj,
          intercept = TRUE)

Arguments

obj	Object to be checked.
intercept	Is the intercept used in the model?

Value

grd	The value of gradient.
hx	The value of equality constraint.
glob	The global value of derivative (grd + hx).
test	Is the condition verified?
lmb	The values of lambda used in the model

Author(s)

Daniele Cuntrera, Luigi Augugliaro, Vito Muggeo

References

Karush, W. (1939). Minima of functions of several variables with inequalities as side constraints. M. Sc. Dissertation. Dept. of Mathematics, Univ. of Chicago.

Examples

p <- 10
n <- 100
X <- cbind(1, matrix(rnorm(n * p), n , p))
b.s <- c(1, rep(0, p))
b.s[sample(2:p, 3)] <- 1
y <- drop(crossprod(t(X), b.s))
out <- cdfPen(X = X, y = y)

KKT <- check_KKT(out)
plot(KKT$test)

penalizedcdf documentation built on Feb. 16, 2023, 6:20 p.m.