# How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference

arXiv: https://arxiv.org/abs/2003.13593 · HTML: https://mlsanity.com/paper/2003.13593/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [GANime: Generating Anime and Manga Character Drawings from Sketches with Deep Learning](https://mlsanity.com/paper/2508.09207/) (2025)
- [Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition](https://mlsanity.com/paper/2509.00077/) (2025)
- [Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision](https://mlsanity.com/paper/2609.16637/) (2026)

## Abstract (arXiv)

The challenge of speeding up deep learning models during the deployment phase has been a large, expensive bottleneck in the modern tech industry. In this paper, we examine the use of both regularization and pruning for reduced computational complexity and more efficient inference in Deep Neural Networks (DNNs). In particular, we apply mixup and cutout regularizations and soft filter pruning to the ResNet architecture, focusing on minimizing floating-point operations (FLOPs). Furthermore, by using regularization in conjunction with network pruning, we show that such a combination makes a substantial improvement over each of the two techniques individually.