HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Sparse regression and support recovery with L2-Boosting algorithms

Abstract : 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.
Document type :
Journal articles
Complete list of metadata

Contributor : Migration Prodinra Connect in order to contact the contributor
Submitted on : Thursday, May 28, 2020 - 11:56:07 AM
Last modification on : Wednesday, June 9, 2021 - 1:18:05 PM




Magali Champion, Christine Cierco-Ayrolles, Sébastien Gadat, Matthieu Vignes. Sparse regression and support recovery with L2-Boosting algorithms. Journal of Statistical Planning and Inference, Elsevier, 2014, 155, pp.19-41. ⟨10.1016/j.jspi.2014.07.006⟩. ⟨hal-02639380⟩



Record views