TR2025-111
AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
-
- "AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent", International Conference on Machine Learning (ICML) workshop, July 2025.BibTeX TR2025-111 PDF
- @inproceedings{Liu2025jul,
- author = {Liu, Jing and Koike-Akino, Toshiaki and Wang, Ye and Mansour, Hassan and Brand, Matthew},
- title = {{AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent}},
- booktitle = {International Conference on Machine Learning (ICML) workshop},
- year = 2025,
- month = jul,
- url = {https://www.merl.com/publications/TR2025-111}
- }
,
- "AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent", International Conference on Machine Learning (ICML) workshop, July 2025.
-
MERL Contacts:
-
Research Areas:
Abstract:
To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this work, we focus on layer-wise post-training quantization and pruning. Drawing connections between activation-aware weight pruning and sparse ap- proximation problems, and motivated by the success of Iterative Hard Thresholding (IHT), we propose a unified method for Activation-aware Weight pruning and quantization via Projected gradient descent (AWP). Our experiments demonstrate that AWP outperforms state-of-the-art LLM pruning and quantization methods. Theoretical convergence guarantees of the proposed method for pruning are also provided.
Related Publication
BibTeX arXiv
- @article{Liu2025jun,
- author = {Liu, Jing and Koike-Akino, Toshiaki and Wang, Ye and Mansour, Hassan and Brand, Matthew},
- title = {{AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent}},
- journal = {arXiv},
- year = 2025,
- month = jun,
- url = {https://arxiv.org/abs/2506.10205}
- }