Greedy function approximation: A gradient boosting machine. (original) (raw)

Open Access

October 2001 Greedy function approximation: A gradient boosting machine.

Jerome H. Friedman

Ann. Statist. 29(5): 1189-1232 (October 2001). DOI: 10.1214/aos/1013203451

Abstract

Function estimation/approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest-descent minimization. A general gradient descent “boosting” paradigm is developed for additive expansions based on any fitting criterion.Specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification. Special enhancements are derived for the particular case where the individual additive components are regression trees, and tools for interpreting such “TreeBoost” models are presented. Gradient boosting of regression trees produces competitive, highly robust, interpretable procedures for both regression and classification, especially appropriate for mining less than clean data. Connections between this approach and the boosting methods of Freund and Shapire and Friedman, Hastie and Tibshirani are discussed.

Citation

Download Citation

Jerome H. Friedman. "Greedy function approximation: A gradient boosting machine.." Ann. Statist. 29 (5) 1189 - 1232, October 2001. https://doi.org/10.1214/aos/1013203451

Information

Published: October 2001

First available in Project Euclid: 8 February 2002

Digital Object Identifier: 10.1214/aos/1013203451

Subjects:

Primary: 62-02, 62-07, 62-08, 62G08, 62H30, 68T10

Keywords: boosting, decision trees, Function estimation, robust nonparametric regression