English

Learning Sparse Additive Models with Interactions in High Dimensions

Machine Learning 2016-04-20 v1 Information Theory math.IT Machine Learning

Abstract

A function f:RdRf: \mathbb{R}^d \rightarrow \mathbb{R} is referred to as a Sparse Additive Model (SPAM), if it is of the form f(x)=lSϕl(xl)f(\mathbf{x}) = \sum_{l \in \mathcal{S}}\phi_{l}(x_l), where S[d]\mathcal{S} \subset [d], Sd|\mathcal{S}| \ll d. Assuming ϕl\phi_l's and S\mathcal{S} to be unknown, the problem of estimating ff from its samples has been studied extensively. In this work, we consider a generalized SPAM, allowing for second order interaction terms. For some S1[d],S2([d]2)\mathcal{S}_1 \subset [d], \mathcal{S}_2 \subset {[d] \choose 2}, the function ff is assumed to be of the form: f(x)=pS1ϕp(xp)+(l,l)S2ϕ(l,l)(xl,xl).f(\mathbf{x}) = \sum_{p \in \mathcal{S}_1}\phi_{p} (x_p) + \sum_{(l,l^{\prime}) \in \mathcal{S}_2}\phi_{(l,l^{\prime})} (x_{l},x_{l^{\prime}}). Assuming ϕp,ϕ(l,l)\phi_{p},\phi_{(l,l^{\prime})}, S1\mathcal{S}_1 and, S2\mathcal{S}_2 to be unknown, we provide a randomized algorithm that queries ff and exactly recovers S1,S2\mathcal{S}_1,\mathcal{S}_2. Consequently, this also enables us to estimate the underlying ϕp,ϕ(l,l)\phi_p, \phi_{(l,l^{\prime})}. We derive sample complexity bounds for our scheme and also extend our analysis to include the situation where the queries are corrupted with noise -- either stochastic, or arbitrary but bounded. Lastly, we provide simulation results on synthetic data, that validate our theoretical findings.

Keywords

Cite

@article{arxiv.1604.05307,
  title  = {Learning Sparse Additive Models with Interactions in High Dimensions},
  author = {Hemant Tyagi and Anastasios Kyrillidis and Bernd Gärtner and Andreas Krause},
  journal= {arXiv preprint arXiv:1604.05307},
  year   = {2016}
}

Comments

23 pages, to appear in Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS) 2016

R2 v1 2026-06-22T13:35:14.658Z