mlsanityData to 7 Oct 2026

Bagging Provides Assumption-free Stability

arXiv 2301.12600 ↗First posted 30 Jan 2023stat.ML cs.LG math.STcited by 18

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 14 of its 52 references that are in the map. First posted on arXiv 30 Jan 2023.

Builds on

14 of 52 references.

References · 14

  1. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 547
  2. 2019Predictive inference with the jackknife+cited by 206
  3. 2013Stabilitycited by 119
  4. 2018Privacy-preserving Predictioncited by 48
  5. 2018The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regressioncited by 45
  6. 2017Iterative Random Forests to detect predictive and stable high-order interactionscited by 42
  7. 2022Bagging is an Optimal PAC Learnercited by 34
  8. 2019The Implicit Regularization of Ordinary Least Squares Ensemblescited by 25
  9. 2021Stable Conformal Prediction Setscited by 19
  10. 2021Black-box tests for algorithmic stabilitycited by 15
  11. 2022Debiased Machine Learning without Sample-Splitting for Stable Estimatorscited by 13
  12. 2022Bagging in overparameterized learning: Risk characterization and risk monotonizationcited by 11
2 more
  1. 2020Derandomizing Knockoffscited by 9
  2. 2022Asymptotics of the Sketched Pseudoinversecited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 6; 2026: 6.

18 papers.

Sort:

  1. 2024Building a stable classifier with the inflated argmaxcited by 8
  2. 2023Stability of Random Forests and Coverage of Random-Forest Prediction Intervalscited by 4
  3. 2026Leave a Window Out: Modifying the Jackknife for Predictive Inference in Time Seriescited by 4
  4. 2025Leave-One-Out Stable Conformal Predictioncited by 3
  5. 2024The Limits of Assumption-free Tests for Algorithm Performancecited by 2
  6. 2024Stabilizing black-box model selection with the inflated argmaxcited by 2
  7. 2024When does Subagging Work?cited by 1
  8. 2024Is Algorithmic Stability Testable? A Unified Framework under Computational Constraintscited by 1
  9. 2025Stability Selection via Variable Decorrelationcited by 1
  10. 2025Assumption-free stability for ranking problemscited by 1
  11. 2026Improving reproducibility by controlling random seed stability in machine learning based estimation via baggingcited by 1
  12. 2025Early wind turbine alarm prediction based on machine learning: AlarmForecastingcited by 0
6 more
  1. 2025A Stable Lassocited by 0
  2. 2025Weighted Conformal Prediction Provides Adaptive and Valid Mask-Conditional Coverage for General Missing Data Mechanismscited by 0
  3. 20262D Stability Selection: Design Jittering for Doubly Stable Feature Selectioncited by 0
  4. 2026Stabilizing black-box algorithms through task-oriented randomizationcited by 0
  5. 2026Algorithmic stability via ensemblingcited by 0
  6. 2026A Comprehensive View of Fairness through Distributional Stabilitycited by 0