A Complete Analysis of the L_1, P Group-Lasso

Abstract

The Group-Lasso is a well-known tool for joint regularization in machine learning methods. While the l_1,2 and the l_{1,\infty} version have been studied in detail and efficient algorithms exist, there are still open questions regarding other l_1,p variants. We characterize conditions for solutions of the l_1,p Group-Lasso for all p-norms with 1 > 2.

Cite

Text

Vogt and Roth. "A Complete Analysis of the L_1, P Group-Lasso." International Conference on Machine Learning, 2012.

Markdown

[Vogt and Roth. "A Complete Analysis of the L_1, P Group-Lasso." International Conference on Machine Learning, 2012.](https://mlanthology.org/icml/2012/vogt2012icml-complete/)

BibTeX

@inproceedings{vogt2012icml-complete,
  title     = {{A Complete Analysis of the L_1, P Group-Lasso}},
  author    = {Vogt, Julia E. and Roth, Volker},
  booktitle = {International Conference on Machine Learning},
  year      = {2012},
  url       = {https://mlanthology.org/icml/2012/vogt2012icml-complete/}
}