# Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning

arXiv: https://arxiv.org/abs/2103.10629 · HTML: https://mlsanity.com/paper/2103.10629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [Comparing Rewinding and Fine-tuning in Neural Network Pruning](https://mlsanity.com/paper/2003.02389/) (2020)
- [Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask](https://mlsanity.com/paper/1905.01067/) (2019)
- [Soft Threshold Weight Reparameterization for Learnable Sparsity](https://mlsanity.com/paper/2002.03231/) (2020)
- [A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1804.03294/) (2018)
- [Bayesian Compression for Deep Learning](https://mlsanity.com/paper/1705.08665/) (2017)
- [Soft Weight-Sharing for Neural Network Compression](https://mlsanity.com/paper/1702.04008/) (2017)
- [Training Sparse Neural Networks](https://mlsanity.com/paper/1611.06694/) (2016)
- [Compressing Neural Networks using the Variational Information Bottleneck](https://mlsanity.com/paper/1802.10399/) (2018)
- [Block-Sparse Recurrent Neural Networks](https://mlsanity.com/paper/1711.02782/) (2017)
- [Exploring the Regularity of Sparse Structure in Convolutional Neural Networks](https://mlsanity.com/paper/1705.08922/) (2017)
- [Balanced Sparsity for Efficient DNN Inference on GPU](https://mlsanity.com/paper/1811.00206/) (2018)
- [Automated Pruning for Deep Neural Network Compression](https://mlsanity.com/paper/1712.01721/) (2017)
- [Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM](https://mlsanity.com/paper/1903.09769/) (2019)

## Abstract (arXiv)

We report, for the first time, on the cascade weight shedding phenomenon in deep neural networks where in response to pruning a small percentage of a network's weights, a large percentage of the remaining is shed over a few epochs during the ensuing fine-tuning phase. We show that cascade weight shedding, when present, can significantly improve the performance of an otherwise sub-optimal scheme such as random pruning. This explains why some pruning methods may perform well under certain circumstances, but poorly under others, e.g., ResNet50 vs. MobileNetV3. We provide insight into why the global magnitude-based pruning, i.e., GMP, despite its simplicity, provides a competitive performance for a wide range of scenarios. We also demonstrate cascade weight shedding's potential for improving GMP's accuracy, and reduce its computational complexity. In doing so, we highlight the importance of pruning and learning-rate schedules. We shed light on weight and learning-rate rewinding methods of re-training, showing their possible connections to the cascade weight shedding and reason for their advantage over fine-tuning. We also investigate cascade weight shedding's effect on the set of kept weights, and its implications for semi-structured pruning. Finally, we give directions for future research.