arXiv cs.AI· Haonan Yang, Yulin He, Zhuo Li·· 12 小时前AI 评分22
EFC：用误差反馈校准时间序列预测
Look Back, Correct Forward: Error Feedback Calibration for Time Series Forecasting
AI 导读
研究者提出 Error Feedback Calibration（EFC），一个完全在测试时运行的确定性事后校正框架，利用已揭示的预测误差为冻结的预测模型提供因果反馈。
正文 · 原文
Abstract:Time series forecasting models are increasingly deployed in continuously evolving environments. After a forecast is issued, future observations gradually arrive and reveal how the model has failed. Existing methods mainly treat such observations as supervision for parameter updates. However, it remains unclear whether verified forecasting errors can themselves provide causal feedback for correcting future predictions. To address this, we introduce Error Feedback Calibration (EFC), a fully test-time framework for deterministic post-hoc correction of time series forecasting. EFC constructs a Causal Error Diagonal (CED) from revealed errors of overlapping historical forecasts, providing a fresh view of the frozen forecaster's recent failure behavior. Then Cumulative Error Transport (CET) maps this error state to future residuals using cumulative estimation, while temporal out-of-sample validation controls the correction strength. Temporal Residual Learning (TRL) further predicts only the residual structure left after CET from recent CED trajectories, rather than relearning the entire forecasting error. Extensive experiments across forecasting backbones and datasets show that EFC broadly improves forecasting performance while substantially controlling harmful over correction.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.22872 [cs.AI] |
| (or arXiv:2610.22872v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22872 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haonan Yang [view email]
[v1]
Fri, 16 Oct 2026 03:22:18 UTC (866 KB)
来源：arXiv cs.AI · arxiv.org