Article Dans Une Revue IEEE Transactions on Information Theory Année : 2014

Optimal Designs for Lasso and Dantzig Selector Using Expander Codes

Résumé

We investigate the high-dimensional regression problem using adjacency matrices of unbalanced expander graphs. In this frame, we prove that the $\ell_{2}$-prediction error and the $\ell_{1}$-risk of the lasso and the Dantzig selector are optimal up to an explicit multiplicative constant. Thus we can estimate a high-dimensional target vector with an error term similar to the one obtained in a situation where one knows the support of the largest coordinates in advance. Moreover, we show that these design matrices have an explicit restricted eigenvalue. Precisely, they satisfy the restricted eigenvalue assumption and the compatibility condition with an explicit constant. Eventually, we capitalize on the recent construction of unbalanced expander graphs due to Guruswami, Umans, and Vadhan, to provide a deterministic polynomial time construction of these design matrices.

Fichier principal
Vignette du fichier
1010.2457 (339.66 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-01027523 , version 1 (14-12-2023)

Licence

Identifiants

Citer

Yohann de Castro. Optimal Designs for Lasso and Dantzig Selector Using Expander Codes. IEEE Transactions on Information Theory, 2014, 60 (11), ⟨10.1109/TIT.2014.2353995⟩. ⟨hal-01027523⟩
125 Consultations
83 Téléchargements

Altmetric

Partager

  • More