Boosting Algorithms: Regularization, Prediction and Model Fitting

TL;DR

This paper offers a statistical perspective on boosting algorithms, focusing on their application to complex models, regularization, and variable selection, supported by an open-source software package for practical implementation.

Contribution

It introduces a comprehensive statistical framework for boosting, emphasizing regularization and model selection, and provides a flexible software package for practical use.

Findings

Effective regularization in high-dimensional models

Implementation of boosting for various statistical models

Open-source software facilitates model fitting and variable selection

Abstract

We present a statistical perspective on boosting. Special emphasis is given to estimating potentially complex parametric or nonparametric models, including generalized linear and additive models as well as regression models for survival analysis. Concepts of degrees of freedom and corresponding Akaike or Bayesian information criteria, particularly useful for regularization and variable selection in high-dimensional covariate spaces, are discussed as well. The practical aspects of boosting procedures for fitting statistical models are illustrated by means of the dedicated open-source software package mboost. This package implements functions which can be used for model fitting, prediction and variable selection. It is flexible, allowing for the implementation of new boosting algorithms optimizing user-specified loss functions.