Papers
arxiv:2510.18784

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

Published on Oct 21
Authors:
,

Abstract

CAGE, a curvature-aware gradient estimation method, improves low-bit quantization-aware training by reducing quantization-induced accuracy loss in large models.

AI-generated summary

Despite significant work on low-bit quantization-aware training (QAT), there is still a large accuracy gap between such techniques and native training. To address this, we introduce CAGE (Curvature-Aware Gradient Estimation), a new QAT method that augments the straight-through estimator (STE) gradient with a curvature-aware correction designed to counteract the loss increase induced by quantization. CAGE is derived from a multi-objective view of QAT that balances loss minimization with adherence to quantization constraints, yielding a principled correction term that depends on local curvature information. On the theoretical side, we introduce the notion of Pareto-optimal solutions for quantized optimization, and establish that CAGE yields strong convergence guarantees in the smooth non-convex setting. In terms of implementation, our approach is optimizer-agnostic, but we provide a highly-efficient implementation that leverages Adam statistics. When pre-training Llama-style models of up to 800M-parameters, CAGE recovers over 10% of the quantization-induced loss increase in the W4A4 regime over outlier-mitigation methods. These results indicate that curvature-aware gradient corrections can bridge the remaining performance gap beyond current outlier-handling methods.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.18784 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/2510.18784 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/2510.18784 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.