Hot eventLive
RACE:残差感知测试时适配的邻居丰富时序基础模型预测
1 reports1 sources3 hr ago updated
Get the story
AI overview
RACE(Residual-Aware Correction of Forecasting Errors)是一个两阶段框架,旨在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。该方法面向邻居丰富的时间序列场景,通过残差感知机制在测试时自适应地修正基础模型的预测偏差。相关成果于 2026-10-02 12:00 发布于 arXiv(Statistics Machine Learning),为一手报道。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
Oct 2, 2026
- arXiv · Statistics Machine LearningRACE: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
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。
Heat trend
There is not enough continuous observation data to draw a trend yet.