轻量级时序预测模型，专为边缘设备稳定推理设计
COMET-SG1: Lightweight Autoregressive Regressor for Edge and Embedded AI
- 通过线性行为编码与确定性状态更新实现稳定预测
- 长时序预测误差显著低于MLP、LSTM等基线模型
- 参数少、支持定点运算，适合嵌入式部署
COMET-SG1 是一种面向边缘和嵌入式 AI 系统的时间序列预测轻量级自回归回归模型。与循环神经网络或基于变压器的序列模型不同，COMET-SG1 采用线性行为空间编码、记忆锚定转移估计和确定性状态更新机制，在完全自回归推断下确保长期预测行为有界，这对边缘部署中随时间累积的预测误差控制至关重要。在非平稳合成时间序列数据上的实验表明，COMET-SG1 在短时预测精度上具有竞争力，同时相比 MLP、LSTM 和 k-近邻基线模型展现出显著更低的长期漂移。其紧凑的参数量和兼容定点算术的操作特性，使其成为边缘与嵌入式 AI 应用中稳定自回归预测的一种实用且可解释的方法。
原文摘要 · Abstract (English)
COMET-SG1 is a lightweight, stability-oriented autoregressive regression model designed for time-series prediction on edge and embedded AI systems. Unlike recurrent neural networks or transformer-based sequence models, COMET-SG1 operates through linear behavior-space encoding, memory-anchored transition estimation, and deterministic state updates. This structure prioritizes bounded long-horizon behavior under fully autoregressive inference, a critical requirement for edge deployment where prediction errors accumulate over time. Experiments on non-stationary synthetic time-series data demonstrate that COMET-SG1 achieves competitive short-horizon accuracy while exhibiting significantly reduced long-horizon drift compared to MLP, LSTM, and k-nearest neighbor baselines. With a compact parameter footprint and operations compatible with fixed-point arithmetic, COMET-SG1 provides a practical and interpretable approach for stable autoregressive prediction in edge and embedded AI applications.
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。