Deep learning models, particularly Transformers, have achieved impressive
results in various domains, including time series forecasting. While existing
time series literature primarily focuses on model architecture modifications
and data augmentation techniques, this paper explores the training schema of
deep learning models for time series; how models are trained regardless of
their architecture. We perform extensive experiments to investigate the
occurrence of deep double descent in several Transformer models trained on
public time series data sets. We demonstrate epoch-wise deep double descent and
that overfitting can be reverted using more epochs. Leveraging these findings,
we achieve state-of-the-art results for long sequence time series forecasting
in nearly 70% of the 72 benchmarks tested. This suggests that many models in
the literature may possess untapped potential. Additionally, we introduce a
taxonomy for classifying training schema modifications, covering data
augmentation, model inputs, model targets, time series per model, and
computational budget.

通过对深度学习模型的训练模式进行广泛实验，在公共时间序列数据集上训练的多个 Transformer 模型中观察到了深度双下降现象，而通过使用更多的 epochs 可以减轻过拟合，取得了接近 72 个基准测试中 70% 的长序列时间序列预测的最新成果；此外，还提出了一个对训练模式修改进行分类的分类法，涵盖了数据增强、模型输入、模型目标、每个模型的时间序列和计算预算。