sparsify a matrix

This implements a quantile based sparsification operation

orthogonalizeAndQSparsify(
  v,
  sparsenessQuantile = 0.5,
  positivity = "either",
  orthogonalize = TRUE,
  softThresholding = FALSE,
  unitNorm = FALSE
)

Arguments

v

input matrix
sparsenessQuantile

quantile to control sparseness - higher is sparser
positivity

restrict to positive or negative solution (beta) weights. choices are positive, negative or either as expressed as a string.
orthogonalize

run gram-schmidt if TRUE.
softThresholding

use soft thresholding
unitNorm

set each vector to unit norm

Value

matrix

Examples


mat<-replicate(100, rnorm(20))
mat = orthogonalizeAndQSparsify( mat )