@article{e7f927a5-931e-456a-8971-5b776d439596,
author = {Jacek Klimaszewski, Marcin  Korzeń},
title = {Optimization of ℓp-regularized Linear Models via Coordinate Descent},
journal = {Schedae Informaticae},
volume = {2016},
number = {Volume 25},
year = {2017},
issn = {1732-3916},
pages = {61-72},keywords = {Classification; Coordinate Descent; Regression; Sparsity},
abstract = {In this paper we demonstrate, how `p-regularized univariate quadratic loss function can be effectively optimized (for 0 6 p 6 1) without approximation of penalty term and provide analytical solution for p = 1 2 . Next we adapt this approach for important multivariate cases like linear and logistic regressions, using Coordinate Descent algorithm. At the end we compare sample complexity of `1 with `p, 0 6 p < 1 regularized models for artificial and real datasets.},
doi = {10.4467/20838476SI.16.005.6186},
url = {https://ejournals.eu/en/journal/schedae-informaticae/article/optimization-of-p-regularized-linear-models-via-coordinate-descent}
}