Tuning parameters in random forests

Breiman's (2001) random forests are a very popular class of learning algorithms often able to produce good predictions even in high-dimensional frameworks, with no need to accurately tune its inner parameters. Unfortunately, there are no theoretical findings to support the default values used f...

Full description

Bibliographic Details
Main Author: Scornet Erwan
Format: Article
Language:English
Published: EDP Sciences 2017-01-01
Series:ESAIM: Proceedings and Surveys
Online Access:https://doi.org/10.1051/proc/201760144