# Learning Compact Convolutional Neural Networks with Nested Dropout

arXiv: https://arxiv.org/abs/1412.7155 · HTML: https://mlsanity.com/paper/1412.7155/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2014.

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

- [Variational Nested Dropout](https://mlsanity.com/paper/2101.11353/) (2021)
- [Information-Ordered Bottlenecks for Adaptive Semantic Compression](https://mlsanity.com/paper/2305.11213/) (2023)

## Abstract (arXiv)

Recently, nested dropout was proposed as a method for ordering representation units in autoencoders by their information content, without diminishing reconstruction cost. However, it has only been applied to training fully-connected autoencoders in an unsupervised setting. We explore the impact of nested dropout on the convolutional layers in a CNN trained by backpropagation, investigating whether nested dropout can provide a simple and systematic way to determine the optimal representation size with respect to the desired accuracy and desired task and data complexity.