PulseAugur
实时 10:12:43
English(EN) GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting

GatedLinear框架提供自适应路由以改进时间序列预测

研究人员推出GatedLinear,一个旨在通过自适应路由互补线性基来改进时间序列预测的新框架。该方法解决了当前深度学习模型常为多样化时间动态使用单一计算主干的局限性。GatedLinear采用三种专业机制——全局趋势季节性、基于差分的增量和相位对齐递归——由三因子分解融合门进行协调。这使得在不同预测模式下实现细粒度的逐点路由,以更小的参数量和可解释的路由模式达到最先进的准确性。 AI

影响 为时间序列预测引入了一种更有效、更具可解释性的方法,有可能在复杂的现实场景中提高准确性。

排序理由 该集群描述了一篇详细介绍时间序列预测新框架的最新研究论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

GatedLinear框架提供自适应路由以改进时间序列预测

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Qitai Tan, Ruiwen Gu, Yilin Su, Mo Li, Xu Lin, Xiao-Ping Zhang ·

    GatedLinear:自适应路由互补线性基用于时间序列预测

    arXiv:2607.09537v1 Announce Type: new Abstract: Time series forecasting requires models to capture diverse, often mutually exclusive, temporal dynamics, from smooth trend continuation to nonstationary drift and strict phase-aligned recurrence. While recent deep learning models ha…

  2. arXiv cs.LG TIER_1 English(EN) · Xiao-Ping Zhang ·

    GatedLinear:自适应路由互补线性基用于时间序列预测

    Time series forecasting requires models to capture diverse, often mutually exclusive, temporal dynamics, from smooth trend continuation to nonstationary drift and strict phase-aligned recurrence. While recent deep learning models have improved accuracy, they typically force these…