Papers
arxiv:2601.19320

StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths

Published on Jan 27
Authors:
,
,
,
,
,
,
,

Abstract

StableQAT presents a novel quantization-aware training framework that improves training stability and efficiency at ultra-low bitwidths through a theoretically grounded surrogate for backpropagation derived from discrete Fourier analysis.

AI-generated summary

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the straight-through estimator (STE) or soft quantizers often suffer from gradient mismatch, instability, or high computational overhead. As such, we propose StableQAT, a unified and efficient QAT framework that stabilizes training in ultra low-bit settings via a novel, lightweight, and theoretically grounded surrogate for backpropagation derived from a discrete Fourier analysis of the rounding operator. StableQAT strictly generalizes STE as the latter arises as a special case of our more expressive surrogate family, yielding smooth, bounded, and inexpensive gradients that improve QAT training performance and stability across various hyperparameter choices. In experiments, StableQAT exhibits stable and efficient QAT at 2-4 bit regimes, demonstrating improved training stability, robustness, and superior performance with negligible training overhead against standard QAT techniques. Our code is available at https://github.com/microsoft/StableQAT.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2601.19320 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2601.19320 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2601.19320 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.