Time-o1: Time-Series Forecasting Needs Transformed Label Alignment

Excerpt

arXiv:2505.17847v3 Announce Type: replace Abstract: Training time-series forecasting models poses unique challenges in loss function design. Most existing approaches adopt temporal mean squared error, but this study reveals two critical limitations: (1) it ignores the presence of label autocorrelation, which biases it from the true label sequence likelihood; (2) it involves excessive number of tasks, which complicates optimization, especially for long-term forecasting. To address these issues, w