Corpus ID: 2759671

# Mind the duality gap: safer rules for the Lasso

@article{Fercoq2015MindTD,
title={Mind the duality gap: safer rules for the Lasso},
author={Olivier Fercoq and A. Gramfort and J. Salmon},
journal={ArXiv},
year={2015},
volume={abs/1505.03410}
}
• Published 2015
• Mathematics, Computer Science
• ArXiv
Screening rules allow to early discard irrelevant variables from the optimization in Lasso problems, or its derivatives, making solvers faster. In this paper, we propose new versions of the so-called $\textit{safe rules}$ for the Lasso. Based on duality gap considerations, our new rules create safe test regions whose diameters converge to zero, provided that one relies on a converging solver. This property helps screening out more variables, for a wider range of regularization parameter values… Expand
96 Citations

#### Figures, Tables, and Topics from this paper

Gap Safe screening rules for sparsity enforcing penalties
• Mathematics, Computer Science
• J. Mach. Learn. Res.
• 2017
Dual Extrapolation for Faster Lasso Solvers
• Computer Science
• ICML 2018
• 2018
GAP Safe Screening Rules for Sparse-Group Lasso
• Computer Science, Mathematics
• NIPS
• 2016
Ensembles of Lasso Screening Rules
• Medicine, Computer Science
• IEEE Transactions on Pattern Analysis and Machine Intelligence
• 2018
Look-Ahead Screening Rules for the Lasso

#### References

SHOWING 1-10 OF 48 REFERENCES
Lasso screening rules via dual polytope projection
• Computer Science, Mathematics
• J. Mach. Learn. Res.
• 2015
Strong rules for discarding predictors in lasso-type problems.
• R. Tibshirani, +4 authors R. Tibshirani
• Mathematics, Medicine
• Journal of the Royal Statistical Society. Series B, Statistical methodology
• 2012
Dynamic Screening: Accelerating First-Order Algorithms for the Lasso and Group-Lasso
• Computer Science, Mathematics
• IEEE Transactions on Signal Processing
• 2015
Screening Tests for Lasso Problems
• Computer Science, Mathematics
• IEEE Transactions on Pattern Analysis and Machine Intelligence
• 2017
A dynamic screening principle for the Lasso
• Computer Science
• 2014 22nd European Signal Processing Conference (EUSIPCO)
• 2014
Complexity Analysis of the Lasso Regularization Path
• Mathematics, Computer Science
• ICML
• 2012
Three structural results on the lasso problem
• Mathematics, Computer Science
• 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
• 2013
Safe Feature Elimination in Sparse Supervised Learning
• Computer Science, Mathematics
• ArXiv
• 2010