The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913979971928064 |
|---|---|
| author | Uhlmann, Jeffrey |
| author_facet | Uhlmann, Jeffrey |
| contents | Quantization is usually regarded as a means to trade quality of performance for reduced compute requirements, i.e., as a suboptimal approximation. However, if examined in terms of a fixed overall resource budget, a very different perspective arises. We introduce Signed-Zero Ternary (SZT), a 2-bit quantization that deterministically provides gradient information with no forward-path penalty. Our analysis provides evidence that it may improve information density compared to non-quantized alternatives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05905 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More) Uhlmann, Jeffrey Machine Learning Quantization is usually regarded as a means to trade quality of performance for reduced compute requirements, i.e., as a suboptimal approximation. However, if examined in terms of a fixed overall resource budget, a very different perspective arises. We introduce Signed-Zero Ternary (SZT), a 2-bit quantization that deterministically provides gradient information with no forward-path penalty. Our analysis provides evidence that it may improve information density compared to non-quantized alternatives. |
| title | The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More) |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.05905 |