实验
实验部分有时候可以引用别人的结果，这个时候可以说：
实验效果比所有的baseline都要好
Autoformer achieves the consistent state-ofthe-art performance in all benchmarks and all prediction length settings (Table 1).
实验效果比绝大多数baseline要好
这里分几种情况:
只有一组效果不好
（论文源自Autoformer）
Under the comparison with extensive baselines, our Autoformer still achieves state-of-the-art performance for the long-term forecasting tasks.
（因为这个实验预测了多个序列，只有最短序列的那一组效果不是最好，所以后面加上了一个定语，for the long-term forecasting）
实验效果没有比别人好时进行分析
- Also, we find that ARIMA [1] performs best in the input-96-predict-96 setting of the Exchange dataset but fails in the long-term setting. This situation of ARIMA can be benefited from its inherent capacity for non-stationary economic data but is limited by the intricate temporal patterns of real-world series.
