# Empirical study of extreme overfitting points of neural networks

arXiv: https://arxiv.org/abs/1906.06295 · HTML: https://mlsanity.com/paper/1906.06295/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2019.

## Built on by (most cited first, 1 of 1)

- [Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data](https://mlsanity.com/paper/2212.13827/) (2022)

## Abstract (arXiv)

In this paper we propose a method of obtaining points of extreme overfitting - parameters of modern neural networks, at which they demonstrate close to 100 % training accuracy, simultaneously with almost zero accuracy on the test sample. Despite the widespread opinion that the overwhelming majority of critical points of the loss function of a neural network have equally good generalizing ability, such points have a huge generalization error. The paper studies the properties of such points and their location on the surface of the loss function of modern neural networks.