# Data-Independent Neural Pruning via Coresets

arXiv: https://arxiv.org/abs/1907.04018 · HTML: https://mlsanity.com/paper/1907.04018/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2019.

## Built on by (most cited first, 30 of 35)

- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [A Fast Post-Training Pruning Framework for Transformers](https://mlsanity.com/paper/2204.09656/) (2022)
- [Coresets for Classification -- Simplified and Strengthened](https://mlsanity.com/paper/2106.04254/) (2021)
- [Gradient-Free Structured Pruning with Unlabeled Data](https://mlsanity.com/paper/2303.04185/) (2023)
- [Pruning Deep Neural Networks from a Sparsity Perspective](https://mlsanity.com/paper/2302.05601/) (2023)
- [Data-Efficient Structured Pruning via Submodular Optimization](https://mlsanity.com/paper/2203.04940/) (2022)
- [Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning](https://mlsanity.com/paper/2308.07209/) (2023)
- [A Unified Approach to Coreset Learning](https://mlsanity.com/paper/2111.03044/) (2021)
- [New Coresets for Projective Clustering and Applications](https://mlsanity.com/paper/2203.04370/) (2022)
- [Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond](https://mlsanity.com/paper/2402.17327/) (2024)
- [Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks](https://mlsanity.com/paper/2110.05667/) (2021)
- [Provable Data Subset Selection For Efficient Neural Network Training](https://mlsanity.com/paper/2303.05151/) (2023)
- [Adversarial Robustness of Streaming Algorithms through Importance Sampling](https://mlsanity.com/paper/2106.14952/) (2021)
- [Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration](https://mlsanity.com/paper/2504.00950/) (2025)
- [Model Preserving Compression for Neural Networks](https://mlsanity.com/paper/2108.00065/) (2021)
- [Fair Wasserstein Coresets](https://mlsanity.com/paper/2311.05436/) (2023)
- [Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective](https://mlsanity.com/paper/2303.02095/) (2023)
- [A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation](https://mlsanity.com/paper/2206.05604/) (2022)
- [AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning](https://mlsanity.com/paper/2603.18492/) (2026)
- [No Dimensional Sampling Coresets for Classification](https://mlsanity.com/paper/2402.05280/) (2024)
- [Nonlinear Initialization Methods for Low-Rank Neural Networks](https://mlsanity.com/paper/2202.00834/) (2022)
- [A Deeper Look into Convolutions via Eigenvalue-based Pruning](https://mlsanity.com/paper/2102.02804/) (2021)
- [One-shot Network Pruning at Initialization with Discriminative Image Patches](https://mlsanity.com/paper/2209.05683/) (2022)
- [STAT: Shrinking Transformers After Training](https://mlsanity.com/paper/2406.00061/) (2024)
- [Training-Free Restoration of Pruned Neural Networks](https://mlsanity.com/paper/2502.08474/) (2025)
- [Provable Pruning for Efficient 3D Gaussian Splatting via Coresets](https://mlsanity.com/paper/2607.02721/) (2026)
- [Pruning with Compensation: Efficient Channel Pruning for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2108.13728/) (2021)
- [i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery](https://mlsanity.com/paper/2112.04905/) (2021)
- [AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction](https://mlsanity.com/paper/2403.08204/) (2024)
- [Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis](https://mlsanity.com/paper/2512.02967/) (2025)

## Abstract (arXiv)

Previous work showed empirically that large neural networks can be significantly reduced in size while preserving their accuracy. Model compression became a central research topic, as it is crucial for deployment of neural networks on devices with limited computational and memory resources. The majority of the compression methods are based on heuristics and offer no worst-case guarantees on the trade-off between the compression rate and the approximation error for an arbitrarily new sample. We propose the first efficient, data-independent neural pruning algorithm with a provable trade-off between its compression rate and the approximation error for any future test sample. Our method is based on the coreset framework, which finds a small weighted subset of points that provably approximates the original inputs. Specifically, we approximate the output of a layer of neurons by a coreset of neurons in the previous layer and discard the rest. We apply this framework in a layer-by-layer fashion from the top to the bottom. Unlike previous works, our coreset is data independent, meaning that it provably guarantees the accuracy of the function for any input x∈ ℝd, including an adversarial one. We demonstrate the effectiveness of our method on popular network architectures. In particular, our coresets yield 90% compression of the LeNet-300-100 architecture on MNIST while improving the accuracy.