Infinitesimal gradient boosting
Abstract
We define infinitesimal gradient boosting as a limit of the popular tree-based gradient boosting algorithm from machine learning. The limit is considered in the vanishing-learning-rate asymptotic, that is when the learning rate tends to zero and the number of gradient trees is rescaled accordingly. For this purpose, we introduce a new class of randomized regression trees bridging totally randomized trees and Extra Trees and using a softmax distribution for binary splitting. Our main result is the convergence of the associated stochastic algorithm and the characterization of the limiting procedure as the unique solution of a nonlinear ordinary differential equation in a infinite dimensional function space. Infinitesimal gradient boosting defines a smooth path in the space of continuous functions along which the training error decreases, the residuals remain centered and the total variation is well controlled.
Cite
@article{arxiv.2104.13208,
title = {Infinitesimal gradient boosting},
author = {Clément Dombry and Jean-Jil Duchamps},
journal= {arXiv preprint arXiv:2104.13208},
year = {2023}
}
Comments
51 pages, 5 figures