# Coreset-Based Neural Network Compression

arXiv: https://arxiv.org/abs/1807.09810 · HTML: https://mlsanity.com/paper/1807.09810/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2018.

## Built on by (most cited first, 27 of 27)

- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Towards Compact CNNs via Collaborative Compression](https://mlsanity.com/paper/2105.11228/) (2021)
- [FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification](https://mlsanity.com/paper/2207.10888/) (2022)
- [Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations](https://mlsanity.com/paper/2504.05586/) (2025)
- [Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions](https://mlsanity.com/paper/2303.08595/) (2023)
- [Coresets for Decision Trees of Signals](https://mlsanity.com/paper/2110.03195/) (2021)
- [Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration](https://mlsanity.com/paper/2504.00950/) (2025)
- [Compressing Models with Few Samples: Mimicking then Replacing](https://mlsanity.com/paper/2201.02620/) (2022)
- [LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification](https://mlsanity.com/paper/2204.02965/) (2022)
- [Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion](https://mlsanity.com/paper/2107.06916/) (2021)
- [Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks](https://mlsanity.com/paper/2409.02134/) (2024)
- [A Deeper Look into Convolutions via Eigenvalue-based Pruning](https://mlsanity.com/paper/2102.02804/) (2021)
- [Efficient Inference via Universal LSH Kernel](https://mlsanity.com/paper/2106.11426/) (2021)
- [Batch Normalization Tells You Which Filter is Important](https://mlsanity.com/paper/2112.01155/) (2021)
- [Filter Pruning based on Information Capacity and Independence](https://mlsanity.com/paper/2303.03645/) (2023)
- [Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection](https://mlsanity.com/paper/2309.16592/) (2023)
- [From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks](https://mlsanity.com/paper/2405.06038/) (2024)
- [Training-Free Restoration of Pruned Neural Networks](https://mlsanity.com/paper/2502.08474/) (2025)
- [Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems](https://mlsanity.com/paper/2201.00063/) (2021)
- [Securing Neural Networks with Knapsack Optimization](https://mlsanity.com/paper/2304.10442/) (2023)
- [A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression](https://mlsanity.com/paper/2309.13077/) (2023)
- [Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum](https://mlsanity.com/paper/2506.07975/) (2025)
- [Improving Model Classification by Optimizing the Training Dataset](https://mlsanity.com/paper/2507.16729/) (2025)
- [A Comprehensive Study of Structural Pruning for Vision Models](https://mlsanity.com/paper/2406.12315/) (2024)
- [Deterministic Coreset for Lp Subspace](https://mlsanity.com/paper/2601.00361/) (2026)
- [Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds](https://mlsanity.com/paper/2606.19941/) (2026)

## Abstract (arXiv)

We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to obtain compression. Our method requires no retraining, is easy to implement, and obtains state-of-the-art compression performance across a wide variety of CNN architectures. Coupled with quantization and Huffman coding, we create networks that provide AlexNet-like accuracy, with a memory footprint that is 832× smaller than the original AlexNet, while also introducing significant reductions in inference time as well. Additionally these compressed networks when fine-tuned, successfully generalize to other domains as well.