Bagging Provides Assumption-free Stability
Machine Learning
2024-04-26 v3 Machine Learning
Statistics Theory
Statistics Theory
Abstract
Bagging is an important technique for stabilizing machine learning models. In this paper, we derive a finite-sample guarantee on the stability of bagging for any model. Our result places no assumptions on the distribution of the data, on the properties of the base algorithm, or on the dimensionality of the covariates. Our guarantee applies to many variants of bagging and is optimal up to a constant. Empirical results validate our findings, showing that bagging successfully stabilizes even highly unstable base algorithms.
Cite
@article{arxiv.2301.12600,
title = {Bagging Provides Assumption-free Stability},
author = {Jake A. Soloff and Rina Foygel Barber and Rebecca Willett},
journal= {arXiv preprint arXiv:2301.12600},
year = {2024}
}