AI Chat AI Image Generator AI Video Text to Speech

Data Augmentation for Imbalanced Regression

02/18/2023

∙

by Samuel Stocksieker, et al.

∙

∙

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.

Samuel Stocksieker
2 publications
Denys Pommeret
6 publications
Arthur Charpentier
17 publications

page 6

page 7

page 13

page 14

page 15

page 22

page 23

page 24

research

∙ 04/12/2023

Towards Understanding How Data Augmentation Works with Imbalanced Data

Data augmentation forms the cornerstone of many modern machine learning ...

0 Damien A. Dablain, et al. ∙

research

∙ 08/05/2023

Generalized Oversampling for Learning from Imbalanced datasets and Associated Theory

In supervised learning, it is quite frequent to be confronted with real ...

0 Samuel Stocksieker, et al. ∙

research

∙ 11/19/2020

Differentiable Data Augmentation with Kornia

In this paper we present a review of the Kornia differentiable data augm...

22 Jian Shi, et al. ∙

research

∙ 04/20/2023

Is augmentation effective to improve prediction in imbalanced text datasets?

Imbalanced datasets present a significant challenge for machine learning...

0 Gabriel O. Assunção, et al. ∙

research

∙ 10/10/2022

The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective

Data augmentation (DA) is a powerful workhorse for bolstering performanc...

0 Chi-Heng Lin, et al. ∙

research

∙ 09/18/2021

Asynchronous and Distributed Data Augmentation for Massive Data Settings

Data augmentation (DA) algorithms are widely used for Bayesian inference...

0 Jiayuan Zhou, et al. ∙

research

∙ 05/31/2023

Building Manufacturing Deep Learning Models with Minimal and Imbalanced Training Data Using Domain Adaptation and Data Augmentation

Deep learning (DL) techniques are highly effective for defect detection ...

0 Adrian Shuai Li, et al. ∙