# lambda: Computes a lambda sequence for the regularization path In nielsrhansen/msgl: Multinomial Sparse Group Lasso

## Description

Computes a decreasing lambda sequence of length d. The sequence ranges from a data determined maximal lambda λ_\textrm{max} to the user inputed lambda.min.

## Usage

 1 2 3 4 5 lambda(x, classes, sampleWeights = NULL, grouping = NULL, groupWeights = NULL, parameterWeights = NULL, alpha = 0.5, d = 100L, standardize = TRUE, lambda.min, intercept = TRUE, sparse.data = is(x, "sparseMatrix"), lambda.min.rel = FALSE, algorithm.config = msgl.standard.config) 

## Arguments

 x design matrix, matrix of size N \times p. classes classes, factor of length N. sampleWeights sample weights, a vector of length N. grouping grouping of features, a vector of length p. Each element of the vector specifying the group of the covariate. groupWeights the group weights, a vector of length m+1 (the number of groups). The first element of the vector is the intercept weight. If groupWeights = NULL default weights will be used. Default weights are 0 for the intercept and √{K\cdot\textrm{number of features in the group}} for all other weights. parameterWeights a matrix of size K \times (p+1). The first column of the matrix is the intercept weights. Default weights are is 0 for the intercept weights and 1 for all other weights. alpha the α value 0 for group lasso, 1 for lasso, between 0 and 1 gives a sparse group lasso penalty. d the length of lambda sequence standardize if TRUE the features are standardize before fitting the model. The model parameters are returned in the original scale. lambda.min the smallest lambda value in the computed sequence. intercept should the model include intercept parameters sparse.data if TRUE x will be treated as sparse, if x is a sparse matrix it will be treated as sparse by default. lambda.min.rel is lambda.min relative to lambda.max ? (i.e. actual lambda min used is lambda.min*lambda.max, with lambda.max the computed maximal lambda value) algorithm.config the algorithm configuration to be used.

## Value

a vector of length d containing the computed lambda sequence.

Martin Vincent

## Examples

 1 2 3 4 5 6 7 data(SimData) # A quick look at the data dim(x) table(classes) lambda <- msgl::lambda(x, classes, alpha = .5, d = 100, lambda.min = 0.01) 

nielsrhansen/msgl documentation built on May 28, 2019, 11:05 a.m.