Linear regression with random projections - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport Technique) Année : 2010

Linear regression with random projections

Odalric-Ambrym Maillard
Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

We consider ordinary (non penalized) least-squares regression where the regression function is chosen in a randomly generated sub-space GP \subset S of finite dimension P, where S is a function space of infinite dimension, e.g. L2([0, 1]^d). GP is defined as the span of P random features that are linear combinations of the basis functions of S weighted by random Gaussian i.i.d. coefficients. We characterize the so-called kernel space K \subset S of the resulting Gaussian process and derive approximation error bounds of order O(||f||^2_K log(P)/P) for functions f \in K approximated in GP . We apply this result to derive excess risk bounds for the least-squares estimate in various spaces. For illustration, we consider regression using the so-called scrambled wavelets (i.e. random linear combinations of wavelets of L2([0, 1]^d)) and derive an excess risk rate O(||f*||_K(logN)/sqrt(N)) which is arbitrarily close to the minimax optimal rate (up to a logarithmic factor) for target functions f* in K = H^s([0, 1]^d), a Sobolev space of smoothness order s > d/2. We describe an efficient implementation using lazy expansions with numerical complexity ˜O(2dN^3/2 logN+N^2), where d is the dimension of the input data and N is the number of data.
Fichier principal
Vignette du fichier
jmlr_blsr.pdf (418.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00483014 , version 1 (12-05-2010)
inria-00483014 , version 2 (29-10-2010)

Identifiants

  • HAL Id : inria-00483014 , version 2

Citer

Odalric-Ambrym Maillard, Rémi Munos. Linear regression with random projections. [Technical Report] 2010, pp.22. ⟨inria-00483014v2⟩
340 Consultations
346 Téléchargements

Partager

Gmail Facebook X LinkedIn More