smoothedLasso: Smoothed LASSO Regression via Nesterov Smoothing

We provide full functionality to compute smoothed LASSO regression estimates. For this, the LASSO objective function is first smoothed using Nesterov smoothing (see Y. Nesterov (2005) <doi:10.1007/s10107-004-0552-5>), resulting in a modified LASSO objective function with explicit gradients everywhere. The smoothed objective function and its gradient are used to minimize it via BFGS, and the obtained minimizer is returned. Using Nesterov smoothing, the smoothed LASSO objective function can be made arbitrarily close to the original (unsmoothed) one. In particular, the Nesterov approach has the advantage that it comes with explicit accuracy bounds, both on the L1/L2 difference of the unsmoothed to the smoothed LASSO objective function as well as on their respective minimizers. A progressive smoothing approach is provided which iteratively smoothes the LASSO, resulting in more stable regression estimates.

Version: 1.3
Imports: Rdpack, Matrix
Published: 2020-06-14
Author: Georg Hahn [aut,cre], Sharon M. Lutz [ctb], Nilanjana Laha [ctb], Christoph Lange [ctb]
Maintainer: Georg Hahn <ghahn at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
CRAN checks: smoothedLasso results


Reference manual: smoothedLasso.pdf
Package source: smoothedLasso_1.3.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release: smoothedLasso_1.3.tgz, r-oldrel: smoothedLasso_1.3.tgz
Old sources: smoothedLasso archive


Please use the canonical form to link to this page.