Supplementary Materials: Autoformer: Decomposition Transformers with Auto-Correlation for Long-term Series Forecasting

Neural Information Processing Systems 

Autoformer achieves sharp improvement over the state-of-the-art on various forecasting horizons. These results show a 60% average MSE reduction over previous state-of-the-art. We fix the input length of Autoformer as 96. For the ILI dataset without obvious periodicity, the larger factor may bring noises. We fix the forecasting horizon as 48 for ILI and 336 for the others.