# Neural Network Pruning Through Constrained Reinforcement Learning

arXiv: https://arxiv.org/abs/2110.08558 · HTML: https://mlsanity.com/paper/2110.08558/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 16 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon](https://mlsanity.com/paper/1705.07565/) (2017)
- [Data-Driven Sparse Structure Selection for Deep Neural Networks](https://mlsanity.com/paper/1707.01213/) (2017)
- [Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications](https://mlsanity.com/paper/1511.06530/) (2015)
- [Fast ConvNets Using Group-wise Brain Damage](https://mlsanity.com/paper/1506.02515/) (2015)
- [Learning Bounds for Risk-sensitive Learning](https://mlsanity.com/paper/2006.08138/) (2020)
- [Structured Pruning of Neural Networks with Budget-Aware Regularization](https://mlsanity.com/paper/1811.09332/) (2018)
- [PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators](https://mlsanity.com/paper/2002.04997/) (2020)
- [Comprehensive Online Network Pruning via Learnable Scaling Factors](https://mlsanity.com/paper/2010.02623/) (2020)
- [Conditional Automated Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/2009.09724/) (2020)
- [Holistic Filter Pruning for Efficient Deep Neural Networks](https://mlsanity.com/paper/2009.08169/) (2020)
- [Teacher-Class Network: A Neural Network Compression Mechanism](https://mlsanity.com/paper/2004.03281/) (2020)

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

- [Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning](https://mlsanity.com/paper/2509.10526/) (2025)

## Abstract (arXiv)

Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often quite tedious and sub-optimal. More recent approaches have instead focused on training auxiliary networks to automatically learn how useful each neuron is however, they often do not take computational limitations into account. In this work, we propose a general methodology for pruning neural networks. Our proposed methodology can prune neural networks to respect pre-defined computational budgets on arbitrary, possibly non-differentiable, functions. Furthermore, we only assume the ability to be able to evaluate these functions for different inputs, and hence they do not need to be fully specified beforehand. We achieve this by proposing a novel pruning strategy via constrained reinforcement learning algorithms. We prove the effectiveness of our approach via comparison with state-of-the-art methods on standard image classification datasets. Specifically, we reduce 83-92.90 of total parameters on various variants of VGG while achieving comparable or better performance than that of original networks. We also achieved 75.09 reduction in parameters on ResNet18 without incurring any loss in accuracy.