Score: 0

The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)

Published: August 8, 2025 | arXiv ID: 2508.05905v1

By: Jeffrey Uhlmann

Potential Business Impact:

Makes computer brains work faster with less power.

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.

Page Count
26 pages

Category
Computer Science:
Machine Learning (CS)