Saved in:
Bibliographic Details
Main Authors: Yuan, Peipei, You, Xinge, Chen, Hong, Zhang, Xuelin, Peng, Qinmu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.06012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914969902120960
author Yuan, Peipei
You, Xinge
Chen, Hong
Zhang, Xuelin
Peng, Qinmu
author_facet Yuan, Peipei
You, Xinge
Chen, Hong
Zhang, Xuelin
Peng, Qinmu
contents Generalized additive models (GAM) have been successfully applied to high dimensional data analysis. However, most existing methods cannot simultaneously estimate the link function, the component functions and the variable interaction. To alleviate this problem, we propose a new sparse additive model, named generalized sparse additive model with unknown link function (GSAMUL), in which the component functions are estimated by B-spline basis and the unknown link function is estimated by a multi-layer perceptron (MLP) network. Furthermore, $\ell_{2,1}$-norm regularizer is used for variable selection. The proposed GSAMUL can realize both variable selection and hidden interaction. We integrate this estimation into a bilevel optimization problem, where the data is split into training set and validation set. In theory, we provide the guarantees about the convergence of the approximate procedure. In applications, experimental evaluations on both synthetic and real world data sets consistently validate the effectiveness of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06012
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalized Sparse Additive Model with Unknown Link Function
Yuan, Peipei
You, Xinge
Chen, Hong
Zhang, Xuelin
Peng, Qinmu
Machine Learning
Generalized additive models (GAM) have been successfully applied to high dimensional data analysis. However, most existing methods cannot simultaneously estimate the link function, the component functions and the variable interaction. To alleviate this problem, we propose a new sparse additive model, named generalized sparse additive model with unknown link function (GSAMUL), in which the component functions are estimated by B-spline basis and the unknown link function is estimated by a multi-layer perceptron (MLP) network. Furthermore, $\ell_{2,1}$-norm regularizer is used for variable selection. The proposed GSAMUL can realize both variable selection and hidden interaction. We integrate this estimation into a bilevel optimization problem, where the data is split into training set and validation set. In theory, we provide the guarantees about the convergence of the approximate procedure. In applications, experimental evaluations on both synthetic and real world data sets consistently validate the effectiveness of the proposed approach.
title Generalized Sparse Additive Model with Unknown Link Function
topic Machine Learning
url https://arxiv.org/abs/2410.06012