To Bag is to Prune

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Coulombe, Philippe Goulet
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912048549462016
author Coulombe, Philippe Goulet
author_facet Coulombe, Philippe Goulet
contents It is notoriously difficult to build a bad Random Forest (RF). Concurrently, RF blatantly overfits in-sample without any apparent consequence out-of-sample. Standard arguments, like the classic bias-variance trade-off or double descent, cannot rationalize this paradox. I propose a new explanation: bootstrap aggregation and model perturbation as implemented by RF automatically prune a latent "true" tree. More generally, randomized ensembles of greedily optimized learners implicitly perform optimal early stopping out-of-sample. So there is no need to tune the stopping point. By construction, novel variants of Boosting and MARS are also eligible for automatic tuning. I empirically demonstrate the property, with simulated and real data, by reporting that these new completely overfitting ensembles perform similarly to their tuned counterparts -- or better.
format Preprint
id arxiv_https___arxiv_org_abs_2008_07063
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle To Bag is to Prune
Coulombe, Philippe Goulet
Machine Learning
Econometrics
It is notoriously difficult to build a bad Random Forest (RF). Concurrently, RF blatantly overfits in-sample without any apparent consequence out-of-sample. Standard arguments, like the classic bias-variance trade-off or double descent, cannot rationalize this paradox. I propose a new explanation: bootstrap aggregation and model perturbation as implemented by RF automatically prune a latent "true" tree. More generally, randomized ensembles of greedily optimized learners implicitly perform optimal early stopping out-of-sample. So there is no need to tune the stopping point. By construction, novel variants of Boosting and MARS are also eligible for automatic tuning. I empirically demonstrate the property, with simulated and real data, by reporting that these new completely overfitting ensembles perform similarly to their tuned counterparts -- or better.
title To Bag is to Prune
topic Machine Learning
Econometrics
url https://arxiv.org/abs/2008.07063