Overblog Follow this blog
Edit post Administration Create my blog
February 28 2013 5 28 /02 /February /2013 17:44

By Odalric-Ambrym Maillard and Rémi Munos,
In Journal of Machine Learning Research 2012, vol:13, pp:2735-2772.

 

Abstract:
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.

 

You can dowload the paper from the JMRL website (here) or from the HAL online open depository* (here).


Bibtex:
@article{MaillardMunos12,
    title = {{Linear Regression with Random Projections}},
    author = {Maillard, Odalric-Ambrym and Munos, R{\'e}mi},   
    affiliation = {SEQUEL - INRIA Lille - Nord Europe},
    pages = {2735-2772},
    journal = {Journal of Machine Learning Research},
    volume = {13},
    year = {2012},
    pdf = {http://hal.archives-ouvertes.fr/hal-00771487/PDF/JMLR\_random\_proj\_2012.pdf},
    url = {http://hal.archives-ouvertes.fr/hal-00771487},
}

 

 

Related publications:

Scrambled Objects for Least-Squares Regression.
Odalric-Ambrym Maillard, Rémi Munos.
In J. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R.S. Zemel, and A. Culotta, editors, Proceedings of the 23rd conference on advances in Neural Information Processing Systems, NIPS '10, pages 1549–1557, 2010.

 

Compressed Least Squares Regression.
Odalric-Ambrym Maillard, Rémi Munos.
In Y. Bengio, D. Schuurmans, J. Lafferty, C. K. I. Williams, and A. Culotta, editors, Proceedings of the 22nd conference on advances in Neural Information Processing Systems,
NIPS '09, pages 1213–1221, 2009.

 

 

  --
* The HAL open-access online archive system seeks to make research results available to the widest audience, independently of the major publisher, and cooperates with other large international archives like arXiv.

Share this post

Repost 0
Published by Odalric-Ambrym Maillard - in Discussing articles
write a comment

comments

Overview

 

Me

Senior Researcher

 

 

The Technion
Faculty of Electrical Engineering,
Fishbach Bldg, Rm. 462
32000 Haifa, ISRAEL
Tel: +972 (0)48293638

Categories