Bagging Provides Assumption-free Stability
From MaRDI portal
Publication:6424742
arXiv2301.12600MaRDI QIDQ6424742
Author name not available (Why is that?)
Publication date: 29 January 2023
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.
Has companion code repository: https://github.com/jake-soloff/subbagging-experiments
This page was built for publication: Bagging Provides Assumption-free Stability
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6424742)