Deep Double Descent for Time Series Forecasting: Avoiding Undertrained Models. (arXiv:2311.01442v1 [cs.LG])

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 …

architecture arxiv augmentation data deep learning domains forecasting literature paper schema series time series time series forecasting training transformers