Bagging Provides Assumption-free Stability
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929326775074816 |
|---|---|
| author | Soloff, Jake A. Barber, Rina Foygel Willett, Rebecca |
| author_facet | Soloff, Jake A. Barber, Rina Foygel Willett, Rebecca |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_12600 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Bagging Provides Assumption-free Stability Soloff, Jake A. Barber, Rina Foygel Willett, Rebecca Machine Learning Statistics Theory 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. |
| title | Bagging Provides Assumption-free Stability |
| topic | Machine Learning Statistics Theory |
| url | https://arxiv.org/abs/2301.12600 |