An Analytical Model for Overparameterized Learning Under Class Imbalance
Abstract
We study class-imbalanced linear classification in a high-dimensional Gaussian mixture model. We develop a tight, closed form approximation for the test error of several practical learning methods, including logit adjustment and class dependent temperature. Our approximation allows us to analytically tune and compare these methods, highlighting how and when they overcome the pitfalls of standard cross-entropy minimization. We test our theoretical findings on simulated data and imbalanced CIFAR10, MNIST and FashionMNIST datasets.
Cite
Text
Mor and Carmon. "An Analytical Model for Overparameterized Learning Under Class Imbalance." Transactions on Machine Learning Research, 2025.Markdown
[Mor and Carmon. "An Analytical Model for Overparameterized Learning Under Class Imbalance." Transactions on Machine Learning Research, 2025.](https://mlanthology.org/tmlr/2025/mor2025tmlr-analytical/)BibTeX
@article{mor2025tmlr-analytical,
title = {{An Analytical Model for Overparameterized Learning Under Class Imbalance}},
author = {Mor, Eliav and Carmon, Yair},
journal = {Transactions on Machine Learning Research},
year = {2025},
url = {https://mlanthology.org/tmlr/2025/mor2025tmlr-analytical/}
}