AMPR

Matlab package of AMPR: AMPR_lasso_matlab. Approximate Message Passing with Resampling (AMPR) for Lasso. Compute the bootstrap average of estimator in Lasso by using a semi-analytic approximate formula called AMPR. Randomization to penalty coefficients is introduced according to stability selection framework. Main quantities to be computed are the mean and variance of the Lasso estimator over the bootstrap samples, and the positive probability of the estimator (probability such that the estimator takes non-zero values).

Keywords for this software

Anything in here will be replaced on browsers that support the canvas element


References in zbMATH (referenced in 1 article , 1 standard article )

Showing result 1 of 1.
Sorted by year (citations)

  1. Obuchi, Tomoyuki; Kabashima, Yoshiyuki: Semi-analytic resampling in Lasso (2019)