L1-Regularized Functional Support Vector Machine

TL;DR

This paper introduces an L1-regularized functional support vector machine for binary classification with multivariate functional covariates, enabling effective feature selection and prediction.

Contribution

It proposes a novel L1-regularized SVM model tailored for multivariate functional data, with an algorithm for fitting and feature selection.

Findings

Good prediction performance demonstrated in simulations

Effective feature selection shown in real-world application

Algorithm successfully identifies relevant covariates

Abstract

In functional data analysis, binary classification with one functional covariate has been extensively studied. We aim to fill in the gap of considering multivariate functional covariates in classification. In particular, we propose an $L_1$-regularized functional support vector machine for binary classification. An accompanying algorithm is developed to fit the classifier. By imposing an $L_1$ penalty, the algorithm enables us to identify relevant functional covariates of the binary response. Numerical results from simulations and one real-world application demonstrate that the proposed classifier enjoys good performance in both prediction and feature selection.