# An Analytical Model for Overparameterized Learning Under Class Imbalance

arXiv: https://arxiv.org/abs/2503.05289 · HTML: https://mlsanity.com/paper/2503.05289/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2025.

## Built on by (most cited first, 2 of 2)

- [Why Loss Re-weighting Works If You Stop Early: Training Dynamics of Unconstrained Features](https://mlsanity.com/paper/2601.12011/) (2026)
- [Comparative Analysis of Different Methods for Classifying Polychromatic Sketches](https://mlsanity.com/paper/2504.08186/) (2025)

## Abstract (arXiv)

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.