用单一可学习算子实现多尺度时间序列建模，提升精度与效率
Generalizing Multi-Scale Time-Series Modeling with a Single Operator
- 提出统一的尺度算子家族，基于尺度空间理论设计可学习高斯核
- 在16个长时序任务中13次最优，训练速度最快提升5.3倍
- 适合需要高效高精度时间序列预测的工业场景
多尺度建模通过捕捉不同时间分辨率下的动态特性，已成为时间序列预测的有效设计原则。然而，现有方法缺乏统一理论基础，且依赖固定离散的尺度划分。为此，本文提出SiGMA（Single Generalized Multi-scale Architecture），通过基于尺度空间理论的可学习离散高斯（LDG）核实现距离感知的尺度变换。在长短期预测基准上全面评估，SiGMA在所有任务中均优于现有先进多尺度模型，尤其在16个长时序设置中有13次表现最佳。此外，相比最强基线，其训练速度最高提升5.3倍，内存消耗最多降低3.8倍。代码已公开于https://github.com/cheonwoolee/SiGMA。
原文摘要 · Abstract (English)
Multi-scale modeling has emerged as an effective design principle for time-series forecasting by capturing temporal dynamics at multiple resolutions. As no principled foundation has been established in the literature, we unify existing scaling methods into a scaling operator family, revealing a fundamental limitation of existing approaches: reliance on fixed and discrete scaling. To address this limitation, we propose SiGMA (Single Generalized Multi-scale Architecture), which enables distance-aware scaling via the learnable discrete Gaussian (LDG) kernel grounded in scale-space theory. We evaluate SiGMA comprehensively on long- and short-term forecasting benchmarks against state-of-the-art multi-scale baselines. SiGMA outperforms all competitors on both tasks, especially achieving the best performance in 13 out of 16 long-term evaluation settings. Beyond accuracy, SiGMA significantly improves training speed by up to 5.3 times and reduces memory consumption by up to 3.8 times over the strongest competitors. Code is available at https://github.com/cheonwoolee/SiGMA.
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。