研究人员推出了PAMod，一个旨在通过处理非平稳数据来改进时间序列预测的新框架。PAMod在归一化特征空间中使用相位幅度调制来模拟周期性分布移位。这种方法可以适应均值和方差的变化，比RevIN等先前方法提供了更稳健的解决方案。实验表明，PAMod以降低的计算成本实现了最先进的结果，并且可以集成到现有的预测模型中。 AI
影响 提高了时间序列预测的准确性和效率，可能改进金融、天气和需求预测等应用。
排序理由 学术论文，介绍了一种新的时间序列预测方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.02938v1 Announce Type: new Abstract: Reliable periodic patterns serve as a fundamental basis for accurate multivariate time series forecasting. However, existing methods either implicitly extract periodicity through complex model architectures (e.g., Transformers) with…
arXiv:2605.00466v1 Announce Type: new Abstract: Real-world time series forecasting faces the fundamental challenge of non-stationary statistical properties, including shifts in mean and variance over time. While reversible instance normalization (RevIN) has shown promise by stati…
Real-world time series forecasting faces the fundamental challenge of non-stationary statistical properties, including shifts in mean and variance over time. While reversible instance normalization (RevIN) has shown promise by stationarizing inputs and denormalizing outputs, it r…