Work

Concentration and excess risk bounds for imbalanced classification with synthetic oversampling

Year: 2025

Type: conference-paper

Abstract: 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

Source: neural information processing systems

DOI: 10.52202/085713-5262

Authors: Touqeer Ahmad, Mohammadreza Mousavi Kalan, François Portier, Gilles Stupfler

Institutions: École Nationale de la Statistique et de l'Analyse de l'Information, Centre de Recherche en Économie et Statistique, Télécom Paris, Université d'Angers

Language: English

Topic: Imbalanced Data Classification Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Centre Henri Lebesgue, Agence Nationale de la Recherche, Région Bretagne