Research map / Architectures and efficiency / Pruning and efficient tuning
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Jian Tang, Wujie Wen, Makan Fardad, Yanzhi Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace iterative prune-and-retrain with ADMM pruning | LeNet-300-100 · MNIST | weights remaining (%): 8% -> 4.37% | Improved |
| replace iterative prune-and-retrain with ADMM pruning | LeNet-5 · MNIST | weights remaining (%): 8% -> 1.4% | Improved |
| replace iterative prune-and-retrain with ADMM pruning | AlexNet · ImageNet ILSVRC-2012 | weights remaining (%): 11% -> 4.76% | Improved |
| target conv layers more aggressively using ADMM, keeping fc ratios as in prior work | AlexNet · ImageNet ILSVRC-2012 | conv1-5 weights remaining (%): 37.1% -> 7.46% | Improved |
| run 25 ADMM iterations instead of 10 (ablation) | ADMM pruning · ImageNet ILSVRC-2012 | weight reduction ratio: 15x -> 18.8x | Improved |
| run 40 ADMM iterations instead of 25 (ablation) | ADMM pruning · ImageNet ILSVRC-2012 | weight reduction ratio: 18.8x -> 21x | Improved |
| run more ADMM iterations (10 to 40) (ablation) | ADMM pruning · ImageNet ILSVRC-2012 | top-5 error (%): 19.8% -> 19.8% | No clear effect |
Closest papers by meaning
- Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks (ICCV 2023 · similarity 0.93)
- “Learning-Compression” Algorithms for Neural Net Pruning (CVPR 2018 · similarity 0.89)
- Harmonious Coexistence of Structured Weight Pruning and Ternarization for Deep Neural Networks (AAAI 2020 · similarity 0.89)
- Computation and Memory-Efficient Model Compression with Gradient Reweighting (NeurIPS 2025 · similarity 0.89)
- Efficient Distortion-Minimized Layerwise Pruning (TPAMI 2025 · similarity 0.89)
- Neural Pruning via Growing Regularization (ICLR 2021 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
