# On the Learnability of Deep Random Networks

arXiv: https://arxiv.org/abs/1904.03866 · HTML: https://mlsanity.com/paper/1904.03866/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 4 of 4)

- [From Local Pseudorandom Generators to Hardness of Learning](https://mlsanity.com/paper/2101.08303/) (2021)
- [Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures](https://mlsanity.com/paper/2205.13647/) (2022)
- [On the hardness of learning under symmetries](https://mlsanity.com/paper/2401.01869/) (2024)
- [Most Neural Networks Are Almost Learnable](https://mlsanity.com/paper/2305.16508/) (2023)

## Abstract (arXiv)

In this paper we study the learnability of deep random networks from both theoretical and practical points of view. On the theoretical front, we show that the learnability of random deep networks with sign activation drops exponentially with its depth. On the practical front, we find that the learnability drops sharply with depth even with the state-of-the-art training methods, suggesting that our stylized theoretical results are closer to reality.