Linear Regression with Random Projections - Archive ouverte HAL Access content directly
Journal Articles Journal of Machine Learning Research Year : 2012

Linear Regression with Random Projections

Rémi Munos
  • Function : Author
  • PersonId : 836863


We investigate a method for regression that makes use of a randomly generated subspace $G_P$ (of finite dimension $P$) of a given large (possibly infinite) dimensional function space $F$, for example, $L_{2}([0,1]^d)$. $G_P$ is defined as the span of $P$ random features that are linear combinations of a basis functions of $F$ weighted by random Gaussian i.i.d.~coefficients. We show practical motivation for the use of this approach, detail the link that this random projections method share with RKHS and Gaussian objects theory and prove, both in deterministic and random design, approximation error bounds when searching for the best regression function in $G_P$ rather than in $F$, and derive excess risk bounds for a specific regression algorithm (least squares regression in $G_P$). This paper stresses the motivation to study such methods, thus the analysis developed is kept simple for explanations purpose and leaves room for future developments.
Fichier principal
Vignette du fichier
JMLR_random_proj_2012.pdf (558.98 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00771487 , version 1 (08-01-2013)


  • HAL Id : hal-00771487 , version 1


Odalric Maillard, Rémi Munos. Linear Regression with Random Projections. Journal of Machine Learning Research, 2012, 13 (1), pp.2735-2772. ⟨hal-00771487⟩
208 View
362 Download


Gmail Facebook Twitter LinkedIn More