用动力系统视角量化时序模型量化误差，提前规划精度分配。
Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score
- 将网络推理过程建模为离散动力系统，分析量化误差传播。
- 提出TQS评分，无需校准数据即可预估各层敏感度。
- 适用于黑盒模型，支持无数据混合精度量化部署。
我们提出轨迹式量化敏感度评分（TQS），从动力系统稳定性角度重思训练后量化（PTQ）。通过将网络前向传播视为离散时间动力系统，TQS刻画量化引入的误差如何在推理时序中传播并放大。与传统方法不同，TQS可独立于量化器选择和位宽分配进行事前敏感度评估，实现对黑盒或已融合算子的模型进行量化预算规划。基于此，我们提出TQS-PTQ框架，无需校准数据或高成本二阶近似，具备灵活的混合精度能力。实验表明，该动力系统视角为资源受限场景下的低精度部署提供了鲁棒且高效路径。
原文摘要 · Abstract (English)
We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By modeling the network's rollout as a discrete-time dynamical system, TQS characterizes how quantization-induced errors propagate and amplify over the rollout horizon. Unlike conventional PTQ methods, where sensitivity analysis is often coupled to the quantization procedure, TQS enables a priori sensitivity estimation decoupled from quantizer selection and bit-width assignment. This separation allows for quantization budget planning even for black-box or compiled networks with fused operators. Building on this, we present TQS-PTQ, a flexible mixed-precision framework that requires no calibration data or costly second-order approximations. Our experiments show that a dynamical-systems perspective provides a robust, high-performing pathway for low-precision deployment in resource-constrained settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。