Estimating composite functions by model selection
Abstract
We consider the problem of estimating a function on for large values of by looking for some best approximation by composite functions of the form . Our solution is based on model selection and leads to a very general approach to solve this problem with respect to many different types of functions and statistical frameworks. In particular, we handle the problems of approximating by additive functions, single and multiple index models, neural networks, mixtures of Gaussian densities (when is a density) among other examples. We also investigate the situation where for functions and belonging to possibly anisotropic smoothness classes. In this case, our approach leads to a completely adaptive estimator with respect to the regularity of .
Cite
@article{arxiv.1102.2818,
title = {Estimating composite functions by model selection},
author = {Yannick Baraud and Lucien Birgé},
journal= {arXiv preprint arXiv:1102.2818},
year = {2013}
}
Comments
37 pages