fit_sparse_regression: Fit a sparse regression model

In inferCSN: Inferring Cell-Specific Gene Regulatory Network

Fit a sparse regression model

Description

Computes the regularization path for the specified loss function and penalty function.

Usage

fit_sparse_regression(
  x,
  y,
  penalty = "L0",
  algorithm = "CD",
  regulators_num = ncol(x),
  cross_validation = FALSE,
  n_folds = 10,
  seed = 1,
  loss = "SquaredError",
  nLambda = 100,
  nGamma = 5,
  gammaMax = 10,
  gammaMin = 1e-04,
  partialSort = TRUE,
  maxIters = 200,
  rtol = 1e-06,
  atol = 1e-09,
  activeSet = TRUE,
  activeSetNum = 3,
  maxSwaps = 100,
  scaleDownFactor = 0.8,
  screenSize = 1000,
  autoLambda = NULL,
  lambdaGrid = list(),
  excludeFirstK = 0,
  intercept = TRUE,
  lows = -Inf,
  highs = Inf,
  ...
)

Arguments

x	The matrix of regulators.
y	The vector of target.
penalty	The type of regularization, default is L0. This can take either one of the following choices: L0, L0L1, and L0L2. For high-dimensional and sparse data, L0L2 is more effective.
algorithm	The type of algorithm used to minimize the objective function, default is CD. Currently CD and CDPSI are supported. The CDPSI algorithm may yield better results, but it also increases running time.
regulators_num	The number of non-zore coefficients, this value will affect the final performance. The maximum support size at which to terminate the regularization path. Recommend setting this to a small fraction of min(n,p) (e.g. 0.05 * min(n,p)) as L0 regularization typically selects a small portion of non-zeros.
cross_validation	Logical value, default is FALSE, whether to use cross-validation.
n_folds	The number of folds for cross-validation, default is 10.
seed	The random seed for cross-validation, default is 1.
loss	The loss function.
nLambda	The number of Lambda values to select.
nGamma	The number of Gamma values to select.
gammaMax	The maximum value of Gamma when using the L0L2 penalty. For the L0L1 penalty this is automatically selected.
gammaMin	The minimum value of Gamma when using the L0L2 penalty. For the L0L1 penalty, the minimum value of gamma in the grid is set to gammaMin * gammaMax. Note that this should be a strictly positive quantity.
partialSort	If TRUE, partial sorting will be used for sorting the coordinates to do greedy cycling. Otherwise, full sorting is used.
maxIters	The maximum number of iterations (full cycles) for CD per grid point.
rtol	The relative tolerance which decides when to terminate optimization, based on the relative change in the objective between iterations.
atol	The absolute tolerance which decides when to terminate optimization, based on the absolute L2 norm of the residuals.
activeSet	If TRUE, performs active set updates.
activeSetNum	The number of consecutive times a support should appear before declaring support stabilization.
maxSwaps	The maximum number of swaps used by CDPSI for each grid point.
scaleDownFactor	This parameter decides how close the selected Lambda values are.
screenSize	The number of coordinates to cycle over when performing initial correlation screening.
autoLambda	Ignored parameter. Kept for backwards compatibility.
lambdaGrid	A grid of Lambda values to use in computing the regularization path.
excludeFirstK	This parameter takes non-negative integers.
intercept	If FALSE, no intercept term is included in the model.
lows	Lower bounds for coefficients.
highs	Upper bounds for coefficients.
...	Parameters for other methods.

Value

An S3 object describing the regularization path

References

Hazimeh, Hussein et al. “L0Learn: A Scalable Package for Sparse Learning using L0 Regularization.” J. Mach. Learn. Res. 24 (2022): 205:1-205:8.

Hazimeh, Hussein and Rahul Mazumder. “Fast Best Subset Selection: Coordinate Descent and Local Combinatorial Optimization Algorithms.” Oper. Res. 68 (2018): 1517-1537.

https://github.com/hazimehh/L0Learn/blob/master/R/fit.R

Examples

data("example_matrix")
fit <- fit_sparse_regression(
  example_matrix[, -1],
  example_matrix[, 1]
)
head(coef(fit))

inferCSN documentation built on Sept. 11, 2024, 9:32 p.m.