Data Augmentation for Imbalanced Regression

@InProceedings{pmlr-v206-stocksieker23a,
  title = 	 {Data Augmentation for Imbalanced Regression},
  author =       {Stocksieker, Samuel and Pommeret, Denys and Charpentier, Arthur},
  booktitle = 	 {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {7774--7799},
  year = 	 {2023},
  editor = 	 {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem},
  volume = 	 {206},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {25--27 Apr},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v206/stocksieker23a/stocksieker23a.pdf},
  url = 	 {https://proceedings.mlr.press/v206/stocksieker23a.html},
  abstract = 	 {In this work, we consider the problem of imbalanced data in a regression framework when the imbalanced phenomenon concerns continuous or discrete covariates. Such a situation can lead to biases in the estimates. In this case, we propose a data augmentation algorithm that combines a weighted resampling (WR) and a data augmentation (DA) procedure. In a first step, the DA procedure permits exploring a wider support than the initial one. In a second step, the WR method drives the exogenous distribution to a target one. We discuss the choice of the DA procedure through a numerical study that illustrates the advantages of this approach. Finally, an actuarial application is studied.}
}