iSolver: SILF Loss

In isotone: Active Set and Generalized PAVA for Isotone Optimization

SILF Loss

Description

Minimizes soft insensitive loss function (SILF) for support vector regression.

Usage

iSolver(z, a, extra)

Arguments

z	Vector containing observed response
a	Matrix with active constraints
extra	List with element y containing the observed response vector, weights with optional observation weights, beta between 0 and 1, and eps > 0

Details

This function is called internally in activeSet by setting mySolver = iSolver.

Value

x	Vector containing the fitted values
lbd	Vector with Lagrange multipliers
f	Value of the target function
gx	Gradient at point x

References

Efron, B. (1991). Regression percentiles using asymmetric squared error loss. Statistica Sinica, 1, 93-125.

See Also

activeSet

Examples

##Fitting isotone regression using active set
set.seed(12345)
y <- rnorm(9)              ##response values
w <- rep(1,9)              ##unit weights
eps <- 2
beta <- 0.4

btota <- cbind(1:8, 2:9)   ##Matrix defining isotonicity (total order)
fit.silf <- activeSet(btota, iSolver, weights = w, y = y, beta = beta, eps = eps)

isotone documentation built on March 7, 2023, 6:58 p.m.