English

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., f(x)=fj(xj)f({\mathbf x}) = \sum f_j(x_j), where xjRx_j\in\mathbb{R} is jj-th component of a sample xRp{\mathbf x}\in \mathbb{R}^p. In this paper, we introduce the total variation (TV) of a function as a measure of the complexity of functions in Lc1(R)L^1_{\rm c}(\mathbb{R})-space. Our analysis shows that a GAM based on TV-regularization exhibits a Rademacher complexity of O(logpm)O(\sqrt{\frac{\log p}{m}}), which is tight in terms of both mm and pp 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).

Keywords

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}
}
R2 v1 2026-06-23T00:16:18.805Z