arXiv · Statistics Machine Learning· Hao-Nan Shi, Tong Wu, Chen-Cong Sun, Yuan Jiang, Han-Jia Ye, De-Chuan Zhan·· 3 小时前AI 评分22
RACE：面向邻居丰富时间序列基础模型预测的残差感知测试时自适应
RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting
AI 导读
summary_zh: RACE（Residual-Aware Correction of Forecasting Errors）是一个两阶段框架，利用同域历史邻居序列对时间序列基础模型（TSFM）的预测误差进行训练-free 校正。
来源：arXiv · Statistics Machine Learning · arxiv.org