# Do we need rebalancing strategies? A theoretical and empirical study around SMOTE and its variants

arXiv: https://arxiv.org/abs/2402.03819 · HTML: https://mlsanity.com/paper/2402.03819/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 78 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees](https://mlsanity.com/paper/2309.09968/) (2023)
- [A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework](https://mlsanity.com/paper/2204.03719/) (2022)
- [Class-Weighted Classification: Trade-offs and Robust Approaches](https://mlsanity.com/paper/2005.12914/) (2020)
- [Why does Throwing Away Data Improve Worst-Group Error?](https://mlsanity.com/paper/2205.11672/) (2022)
- [Minimax optimal rates for Mondrian trees and forests](https://mlsanity.com/paper/1803.05784/) (2018)
- [To SMOTE, or not to SMOTE?](https://mlsanity.com/paper/2201.08528/) (2022)
- [Analysis of purely random forests bias](https://mlsanity.com/paper/1407.3939/) (2014)
- [Sharp error bounds for imbalanced classification: how many examples in the minority class?](https://mlsanity.com/paper/2310.14826/) (2023)
- [Partial Resampling of Imbalanced Data](https://mlsanity.com/paper/2207.04631/) (2022)

## Built on by (most cited first, 5 of 5)

- [Bias-Corrected Data Synthesis for Imbalanced Learning](https://mlsanity.com/paper/2510.26046/) (2025)
- [Concentration and excess risk bounds for imbalanced classification with synthetic oversampling](https://mlsanity.com/paper/2510.20472/) (2025)
- [Harnessing Mixed Features for Imbalance Data Oversampling: Application to Bank Customers Scoring](https://mlsanity.com/paper/2503.22730/) (2025)
- [Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning](https://mlsanity.com/paper/2603.13927/) (2026)
- [Synthetic minority data is redundant or invalid: a data-dependent validity theory and a de-biased test](https://mlsanity.com/paper/2607.20787/) (2026)

## Abstract (arXiv)

Synthetic Minority Oversampling Technique (SMOTE) is a common rebalancing strategy for handling imbalanced tabular data sets. However, few works analyze SMOTE theoretically. In this paper, we derive several non-asymptotic upper bound on SMOTE density. From these results, we prove that SMOTE (with default parameter) tends to copy the original minority samples asymptotically. We confirm and illustrate empirically this first theoretical behavior on a real-world data-set.bFurthermore, we prove that SMOTE density vanishes near the boundary of the support of the minority class distribution. We then adapt SMOTE based on our theoretical findings to introduce two new variants. These strategies are compared on 13 tabular data sets with 10 state-of-the-art rebalancing procedures, including deep generative and diffusion models. One of our key findings is that, for most data sets, applying no rebalancing strategy is competitive in terms of predictive performances, would it be with LightGBM, tuned random forests or logistic regression. However, when the imbalance ratio is artificially augmented, one of our two modifications of SMOTE leads to promising predictive performances compared to SMOTE and other state-of-the-art strategies.