sgs (version 0.3.5)

fit_goscar_cv: Fit a gOSCAR model using k-fold cross-validation.

Description

Function to fit a pathwise solution of group OSCAR (gOSCAR) models using k-fold cross-validation. Supports both linear and logistic regression, both with dense and sparse matrix implementations.

Usage

fit_goscar_cv(
  X,
  y,
  groups,
  type = "linear",
  lambda = "path",
  path_length = 20,
  min_frac = 0.05,
  nfolds = 10,
  backtracking = 0.7,
  max_iter = 5000,
  max_iter_backtracking = 100,
  tol = 1e-05,
  standardise = "l2",
  intercept = TRUE,
  error_criteria = "mse",
  screen = TRUE,
  verbose = FALSE,
  w_weights = NULL
)

Value

A list containing:

errors

A table containing fitting information about the models on the path.

all_models

Fitting information for all models fit on the path, which is a "gslope" object type.

fit

The 1se chosen model, which is a "gslope" object type.

best_lambda

The value of \(\lambda\) which generated the chosen model.

best_lambda_id

The path index for the chosen model.

Arguments

X

Input matrix of dimensions \(n \times p\). Can be a sparse matrix (using class "sparseMatrix" from the Matrix package).

y

Output vector of dimension \(n\). For type="linear" should be continuous and for type="logistic" should be a binary variable.

groups

A grouping structure for the input data. Should take the form of a vector of group indices.

type

The type of regression to perform. Supported values are: "linear" and "logistic".

lambda

The regularisation parameter. Defines the level of sparsity in the model. A higher value leads to sparser models:

• "path" computes a path of regularisation parameters of length "path_length". The path will begin just above the value at which the first predictor enters the model and will terminate at the value determined by "min_frac".

• User-specified single value or sequence. Internal scaling is applied based on the type of standardisation. The returned "lambda" value will be the original unscaled value(s).

path_length

The number of \(\lambda\) values to fit the model for. If "lambda" is user-specified, this is ignored.

min_frac

Smallest value of \(\lambda\) as a fraction of the maximum value. That is, the final \(\lambda\) will be "min_frac" of the first \(\lambda\) value.

nfolds

The number of folds to use in cross-validation.

backtracking

The backtracking parameter, \(\tau\), as defined in Pedregosa and Gidel (2018).

max_iter

Maximum number of ATOS iterations to perform.

max_iter_backtracking

Maximum number of backtracking line search iterations to perform per global iteration.

tol

Convergence tolerance for the stopping criteria.

standardise

Type of standardisation to perform on X:

• "l2" standardises the input data to have \(\ell_2\) norms of one.

• "l1" standardises the input data to have \(\ell_1\) norms of one.

• "sd" standardises the input data to have standard deviation of one.

• "none" no standardisation applied.

intercept

Logical flag for whether to fit an intercept.

error_criteria

The criteria used to discriminate between models along the path. Supported values are: "mse" (mean squared error) and "mae" (mean absolute error).

screen

Logical flag for whether to apply screening rules (see Feser and Evangelou (2024)). Screening discards irrelevant groups before fitting, greatly improving speed.

verbose

Logical flag for whether to print fitting information.

w_weights

Optional vector for the group penalty weights. Overrides the OSCAR penalties when specified. When entering custom weights, these are multiplied internally by \(\lambda\). To void this behaviour, set \(\lambda = 1\).

Details

Fits gOSCAR models under a pathwise solution using adaptive three operator splitting (ATOS), picking the 1se model as optimum. Warm starts are implemented.

References

Bao, R., Gu B., Huang, H. (2020). Fast OSCAR and OWL Regression via Safe Screening Rules, https://proceedings.mlr.press/v119/bao20b

Feser, F., Evangelou, M. (2024). Strong screening rules for group-based SLOPE models, https://proceedings.mlr.press/v80/pedregosa18a.html

See Also

fit_goscar()

Other gSLOPE-methods: coef.sgs(), fit_goscar(), fit_gslope(), fit_gslope_cv(), plot.sgs(), predict.sgs(), print.sgs()

Other model-selection: as_sgs(), fit_gslope_cv(), fit_sgo_cv(), fit_sgs_cv(), scaled_sgs()

Examples

# specify a grouping structure
groups = c(1,1,1,2,2,3,3,3,4,4)
# generate data
data =  gen_toy_data(p=10, n=5, groups = groups, seed_id=3,group_sparsity=1)
# run gOSCAR with cross-validation
cv_model = fit_goscar_cv(X = data$X, y = data$y, groups=groups, type = "linear", path_length = 5, 
nfolds=5, min_frac = 0.05, standardise="l2",intercept=TRUE,verbose=TRUE)