Infinitesimal gradient boosting
Dombry, Clément, Duchamps, Jean-Jil
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.
Apr-26-2021
- Country:
- North America > United States
- New York (0.04)
- Rhode Island > Providence County
- Providence (0.04)
- New Jersey > Hudson County
- Hoboken (0.04)
- California > San Francisco County
- San Francisco (0.14)
- Europe > France
- Bourgogne-Franche-Comté > Doubs > Besançon (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report (0.82)