# Concentration and excess risk bounds for imbalanced classification with synthetic oversampling

arXiv: https://arxiv.org/abs/2510.20472 · HTML: https://mlsanity.com/paper/2510.20472/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 15 of 15)

- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Size-Independent Sample Complexity of Neural Networks](https://mlsanity.com/paper/1712.06541/) (2017)
- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [Class-Weighted Classification: Trade-offs and Robust Approaches](https://mlsanity.com/paper/2005.12914/) (2020)
- [LoRAS: An oversampling approach for imbalanced datasets](https://mlsanity.com/paper/1908.08346/) (2019)
- [Kernel density estimation based sampling for imbalanced class distribution](https://mlsanity.com/paper/1910.07842/) (2019)
- [Achieving the time of 1-NN, but the accuracy of k-NN](https://mlsanity.com/paper/1712.02369/) (2017)
- [Logistic Regression for Massive Data with Rare Events](https://mlsanity.com/paper/2006.00683/) (2020)
- [Imbalanced classification: a paradigm-based review](https://mlsanity.com/paper/2002.04592/) (2020)
- [Nearest Neighbor Sampling for Covariate Shift Adaptation](https://mlsanity.com/paper/2312.09969/) (2023)
- [Do we need rebalancing strategies? A theoretical and empirical study around SMOTE and its variants](https://mlsanity.com/paper/2402.03819/) (2024)
- [Sharp error bounds for imbalanced classification: how many examples in the minority class?](https://mlsanity.com/paper/2310.14826/) (2023)
- [Distribution-Free Rates in Neyman-Pearson Classification](https://mlsanity.com/paper/2402.09560/) (2024)
- [Nearest neighbor empirical processes](https://mlsanity.com/paper/2110.15083/) (2021)
- [Optimal Downsampling for Imbalanced Classification with Generalized Linear Models](https://mlsanity.com/paper/2410.08994/) (2024)

## Built on by (most cited first, 4 of 4)

- [Bias-Corrected Data Synthesis for Imbalanced Learning](https://mlsanity.com/paper/2510.26046/) (2025)
- [Synthetic Augmentation in Imbalanced Learning: When It Helps, When It Hurts, and How Much to Add](https://mlsanity.com/paper/2601.16120/) (2026)
- [When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?](https://mlsanity.com/paper/2606.26053/) (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 oversampling of minority examples using SMOTE and its variants is a leading strategy for addressing imbalanced classification problems. Despite the success of this approach in practice, its theoretical foundations remain underexplored. We develop a theoretical framework to analyze the behavior of SMOTE and related methods when classifiers are trained on synthetic data. We first derive a uniform concentration bound on the discrepancy between the empirical risk over synthetic minority samples and the population risk on the true minority distribution. We then provide a nonparametric excess risk guarantee for kernel-based classifiers trained using such synthetic data. These results lead to practical guidelines for better parameter tuning of both SMOTE and the downstream learning algorithm. Numerical experiments are provided to illustrate and support the theoretical findings