lambda_max: Compute the smallest lambda for which 0 is solution (i.e, the...

In jpvert/droplasso: Dropout lasso

Description

Compute the smallest lambda for which 0 is solution (i.e, the largest lambda of the regularization path). Check the paper for the derivation. Note that in the case of logistic loss, we assume the class coded as 0/1; and in the case of gaussian loss, we consider 1/2*RSS

Usage

lambda_max(x, y, family = c("gaussian", "binomial"))

Arguments

x	Input matrix, of dimension nobs x nvars; each row is an observation vector.
y	Response variable, a vector of length nobs of quantitative values for family="gaussian", or of factors with two levels for family="binomial".
family	Response type. family="gaussian" (default) for least squares regression, family="binomial" for logistic regression

jpvert/droplasso documentation built on May 6, 2019, 7:17 a.m.