Scrambled Objects for Least-Squares Regression.

2010, Discussing articles

Odalric-Ambrym Maillard, Rémi Munos.
In NIPS ’10, pages 1549–1557, 2010.



We consider least-squares regression using a randomly generated subspace G_P \subset F of finite dimension P,  where F is a function space of infinite dimension, e.g. L2([0, 1]^d). G_P 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). As a result, given N data, the least-squares estimate \hat g built from P scrambled wavelets has excess risk ||f^* − \hat g||2 P = O(||f^*||2_{H_s([0,1]^d)}(logN)/P + P(logN)/N) for target functions f^* \in H_s([0, 1]^d) of smoothness order s > d/2. An interesting aspect of the resulting bounds is that they do not depend on the distribution P from which the data are generated, which is important in a statistical regression setting considered here. Randomization enables to adapt to any possible distribution. We conclude by describing an efficient numerical implementation using lazy expansions with numerical complexity \tilde O (2dN^3/2 logN + N^2), where d is the dimension of the input space.

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

title = {Scrambled Objects for Least-Squares Regression},
author = {Odalric Maillard and R\'{e}mi Munos},
booktitle = {Advances in Neural Information Processing Systems 23},
editor = {J.D. Lafferty and C.K.I. Williams and J. Shawe-Taylor and R.S. Zemel and A. Culotta},
pages = {1549–1557},
year = {2010},
publisher = {Curran Associates, Inc.},
url = {}