Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models
Miaoxi Zhu, Qihuang Zhong, Li Shen, Liang Ding, Juhua Liu, Bo Du, Dacheng Tao
Abstract
Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to security and privacy concerns has emerged the demand for zero-shot quantization. Most of the cutting-edge zero-shot quantization methods primarily 1) apply to computer vision tasks, and 2) neglect of overfitting problem in the generative adversarial learning process, leading to sub-optimal performance. Motivated by this, we propose a novel zero-shot sharpness-aware quantization (ZSAQ) framework for the zero-shot quantization of various PLMs. The key algorithm in solving ZSAQ is the SAM-SGA optimization, which aims to improve the quantization accuracy and model generalization via optimizing a minimax problem. We theoretically prove the convergence rate for the minimax optimization problem and this result can be applied to other nonconvex-PL minimax optimization frameworks. Extensive experiments on 11 tasks demonstrate that our method brings consistent and significant performance gains on both discriminative and generative PLMs, i.e., up to +6.98 average score. Furthermore, we empirically validate that our method can effectively improve the model generalization.- Anthology ID:
- 2023.emnlp-main.696
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11305–11327
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.696
- DOI:
- 10.18653/v1/2023.emnlp-main.696
- Cite (ACL):
- Miaoxi Zhu, Qihuang Zhong, Li Shen, Liang Ding, Juhua Liu, Bo Du, and Dacheng Tao. 2023. Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11305–11327, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models (Zhu et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2023.emnlp-main.696.pdf