subgradient: subgradient

In snnR: Sparse Neural Networks for Genomic Selection in Animal Breeding

Description

This function obtains the minimum-norm subgradient of the approximated square error with L1 norm penalty or L2 norm penalty.

Usage

subgradient(w, X, y, nHidden, lambda, lambda2)

Arguments

w	(numeric, n) weights and biases.
X	(numeric, n x p) incidence matrix.
y	(numeric, n) the response data-vector.
nHidden	(positive integer, 1 x h) matrix, h indicates the number of hidden-layers and nHidden[1,h] indicates the neurons of the h-th hidden-layer.
lambda	(numeric,n) lagrange multiplier for L1 norm penalty on parameters.
lambda2	(numeric,n) lagrange multiplier for L2 norm penalty on parameters.

Details

It is based on choosing a subgradient with minimum norm as a steepest descent direction and taking a step resembling Newton iteration in this direction with a Hessian approximation.

Value

A vector with the subgradient values.

snnR documentation built on May 2, 2019, 8:54 a.m.