Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912226883928064 |
|---|---|
| author | Wen, Yuqiao Cao, Yanshuai Mou, Lili |
| author_facet | Wen, Yuqiao Cao, Yanshuai Mou, Lili |
| contents | Large language models have been increasing in size due to their success in a wide range of applications. This calls for a pressing need to reduce memory usage to make them more accessible. Post-training quantization is a popular technique which uses fewer bits (e.g., 4--8 bits) to represent the model without retraining it. However, it remains a challenging task to perform quantization in an ultra-low-bit setup (e.g., 2 bits). In this paper, we propose InvarExplore, a unified framework that systematically explores different model invariance at the same time, allowing us to take advantage of the synergy between each type of invariance. Importantly, InvarExplore features a discrete search algorithm that enables us to explore permutation invariance, which is under-studied as it cannot be optimized with gradient-based methods. Results show that InvarExplore is compatible with existing state-of-the-art methods, achieving an add-on performance improvement over strong competing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06844 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization Wen, Yuqiao Cao, Yanshuai Mou, Lili Machine Learning Artificial Intelligence Computation and Language I.2.7; I.2.6; I.2.m; I.5.1; I.7.m Large language models have been increasing in size due to their success in a wide range of applications. This calls for a pressing need to reduce memory usage to make them more accessible. Post-training quantization is a popular technique which uses fewer bits (e.g., 4--8 bits) to represent the model without retraining it. However, it remains a challenging task to perform quantization in an ultra-low-bit setup (e.g., 2 bits). In this paper, we propose InvarExplore, a unified framework that systematically explores different model invariance at the same time, allowing us to take advantage of the synergy between each type of invariance. Importantly, InvarExplore features a discrete search algorithm that enables us to explore permutation invariance, which is under-studied as it cannot be optimized with gradient-based methods. Results show that InvarExplore is compatible with existing state-of-the-art methods, achieving an add-on performance improvement over strong competing methods. |
| title | Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization |
| topic | Machine Learning Artificial Intelligence Computation and Language I.2.7; I.2.6; I.2.m; I.5.1; I.7.m |
| url | https://arxiv.org/abs/2502.06844 |