Champion, Magali, Cierco, Christine, Gadat, Sébastien and Vignes, Matthieu (2014) Sparse regression and support recovery with L2-Boosting algorithms. Journal of Statistical Planning and Inference, 155. pp. 19-41.

Full text not available from this repository.
Identification Number : 10.1016/j.jspi.2014.07.006


This paper focuses on the analysis of L2L2-Boosting algorithms for linear regressions. Consistency results were obtained for high-dimensional models when the number of predictors grows exponentially with the sample size nn. We propose a new result for Weak Greedy Algorithms that deals with the support recovery, provided that reasonable assumptions on the regression parameter are fulfilled. For the sake of clarity, we also present some results in the deterministic case. Finally, we propose two multi-task versions of L2L2-Boosting for which we can extend these stability results, provided that assumptions on the restricted isometry of the representation and on the sparsity of the model are fulfilled. The interest of these two algorithms is demonstrated on various datasets.

Item Type: Article
Language: English
Date: December 2014
Refereed: Yes
Divisions: TSE-R (Toulouse)
Site: UT1
Date Deposited: 16 Mar 2015 14:50
Last Modified: 02 Apr 2021 15:49
OAI Identifier:
View Item