Scrambled Objects for Least-Squares Regression

O. A. Maillard 1 R. Munos 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : We consider least-squares regression using a randomly generated subspace G of finite dimension P, where F is a function space of infinite dimension, e.g.~L₂([0,1]^d). G is defined as the span of P random features that are linear combinations of the basis functions of F weighted by random Gaussian i.i.d.~coefficients. In particular, we consider multi-resolution random combinations at all scales of a given mother function, such as a hat function or a wavelet. In this latter case, the resulting Gaussian objects are called scrambled wavelets and we show that they enable to approximate functions in Sobolev spaces H^s([0,1]^d). An interesting aspect of the resulting bounds is that they do not depend on the distribution from which the data are generated, which is important in a statistical regression setting considered here. Randomization enables to adapt to any possible distribution.
Type de document :
Communication dans un congrès
Advances in Neural Information Processing Systems, 2010, Granada, Spain. 2010
Liste complète des métadonnées
Contributeur : Philippe Preux <>
Soumis le : vendredi 7 février 2014 - 08:23:57
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13


  • HAL Id : hal-00943121, version 1



O. A. Maillard, R. Munos. Scrambled Objects for Least-Squares Regression. Advances in Neural Information Processing Systems, 2010, Granada, Spain. 2010. 〈hal-00943121〉



Consultations de la notice