Statistical Learnability of Generalized Additive Models based on Total Variation Regularization
Machine Learning
2018-02-19 v2 Machine Learning
Abstract
A generalized additive model (GAM, Hastie and Tibshirani (1987)) is a nonparametric model by the sum of univariate functions with respect to each explanatory variable, i.e., , where is -th component of a sample . In this paper, we introduce the total variation (TV) of a function as a measure of the complexity of functions in -space. Our analysis shows that a GAM based on TV-regularization exhibits a Rademacher complexity of , which is tight in terms of both and in the agnostic case of the classification problem. In result, we obtain generalization error bounds for finite samples according to work by Bartlett and Mandelson (2002).
Cite
@article{arxiv.1802.03001,
title = {Statistical Learnability of Generalized Additive Models based on Total Variation Regularization},
author = {Shin Matsushima},
journal= {arXiv preprint arXiv:1802.03001},
year = {2018}
}