# DECORE: Deep Compression with Reinforcement Learning

arXiv: https://arxiv.org/abs/2106.06091 · HTML: https://mlsanity.com/paper/2106.06091/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 76 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 30 of 49)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [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)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)

## Built on by (most cited first, 29 of 29)

- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Continual Semantic Segmentation with Automatic Memory Sample Selection](https://mlsanity.com/paper/2304.05015/) (2023)
- [HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks](https://mlsanity.com/paper/2301.09422/) (2023)
- [An Information Theory-inspired Strategy for Automatic Network Pruning](https://mlsanity.com/paper/2108.08532/) (2021)
- [Semantic Compression With Large Language Models](https://mlsanity.com/paper/2304.12512/) (2023)
- [Action Tokenizer Matters in In-Context Imitation Learning](https://mlsanity.com/paper/2503.01206/) (2025)
- [OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2412.16849/) (2024)
- [Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations](https://mlsanity.com/paper/2207.03824/) (2022)
- [An Effective Information Theoretic Framework for Channel Pruning](https://mlsanity.com/paper/2408.16772/) (2024)
- [Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML](https://mlsanity.com/paper/2305.14109/) (2023)
- [Effective Layer Pruning Through Similarity Metric Perspective](https://mlsanity.com/paper/2405.17081/) (2024)
- [Compact Model Training by Low-Rank Projection with Energy Transfer](https://mlsanity.com/paper/2204.05566/) (2022)
- [Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition](https://mlsanity.com/paper/2405.03089/) (2024)
- [LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch](https://mlsanity.com/paper/2309.14157/) (2023)
- [Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch](https://mlsanity.com/paper/2505.23763/) (2025)
- [A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression](https://mlsanity.com/paper/2309.13077/) (2023)
- [AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction](https://mlsanity.com/paper/2403.08204/) (2024)
- [Hardware-Aware DNN Compression for Homogeneous Edge Devices](https://mlsanity.com/paper/2501.15240/) (2025)
- [LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation](https://mlsanity.com/paper/2507.21573/) (2025)
- [Reduced storage direct tensor ring decomposition for convolutional neural networks compression](https://mlsanity.com/paper/2405.10802/) (2024)
- [Unified Framework for Pre-trained Neural Network Compression via Decomposition and Optimized Rank Selection](https://mlsanity.com/paper/2409.03555/) (2024)
- [Layer Pruning with Consensus: A Triple-Win Solution](https://mlsanity.com/paper/2411.14345/) (2024)
- [CoSeP: Complementary Separability Pruning via Class-Separability Clustering](https://mlsanity.com/paper/2505.13225/) (2025)
- [Pruning Everything, Everywhere, All at Once](https://mlsanity.com/paper/2506.04513/) (2025)
- [FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference](https://mlsanity.com/paper/2508.02291/) (2025)
- [FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning](https://mlsanity.com/paper/2511.18977/) (2025)
- [Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning](https://mlsanity.com/paper/2602.12146/) (2026)
- [EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI](https://mlsanity.com/paper/2607.06982/) (2026)
- [Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning](https://mlsanity.com/paper/2607.11473/) (2026)

## Abstract (arXiv)

Deep learning has become an increasingly popular and powerful methodology for modern pattern recognition systems. However, many deep neural networks have millions or billions of parameters, making them untenable for real-world applications due to constraints on memory size or latency requirements. As a result, efficient network compression techniques are often required for the widespread adoption of deep learning methods. We present DECORE, a reinforcement learning-based approach to automate the network compression process. DECORE assigns an agent to each channel in the network along with a light policy gradient method to learn which neurons or channels to be kept or removed. Each agent in the network has just one parameter (keep or drop) to learn, which leads to a much faster training process compared to existing approaches. DECORE provides state-of-the-art compression results on various network architectures and various datasets. For example, on the ResNet-110 architecture, it achieves a 64.8% compression and 61.8% FLOPs reduction as compared to the baseline model without any accuracy loss on the CIFAR-10 dataset. It can reduce the size of regular architectures like the VGG network by up to 99% with just a small accuracy drop of 2.28%. For a larger dataset like ImageNet with just 30 epochs of training, it can compress the ResNet-50 architecture by 44.7% and reduce FLOPs by 42.3%, with just a 0.69% drop on Top-5 accuracy of the uncompressed model. We also demonstrate that DECORE can be used to search for compressed network architectures based on various constraints, such as memory and FLOPs.