# Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers

arXiv: https://arxiv.org/abs/1802.05747 · HTML: https://mlsanity.com/paper/1802.05747/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2018.

## Built on by (most cited first, 4 of 4)

- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization](https://mlsanity.com/paper/2206.01198/) (2022)
- [Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?](https://mlsanity.com/paper/2102.11068/) (2021)
- [All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management](https://mlsanity.com/paper/2212.05122/) (2022)

## Abstract (arXiv)

We present a systematic weight pruning framework of deep neural networks (DNNs) using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a constrained nonconvex optimization problem, and then adopt the ADMM framework for systematic weight pruning. We show that ADMM is highly suitable for weight pruning due to the computational efficiency it offers. We achieve a much higher compression ratio compared with prior work while maintaining the same test accuracy, together with a faster convergence rate. Our models are released at https://github.com/KaiqiZhang/admm-pruning