Sequence-to-sequence models based on LSTM and GRU are a most popular choice for forecasting time series data reaching state-of-the-art performance. Training such models can be delicate though. The two most common training strategies within this context are teacher forcing (TF) and free running (FR). TF can be used to help the model to converge faster but may provoke an exposure bias issue due to a discrepancy between training and inference phase. FR helps to avoid this but does not necessarily lead to better results, since it tends to make the training slow and unstable instead. Scheduled sampling was the first approach tackling these issues by picking the best from both worlds and combining it into a curriculum learning (CL) strategy. Although scheduled sampling seems to be a convincing alternative to FR and TF, we found that, even if parametrized carefully, scheduled sampling may lead to premature termination of the training when applied for time series forecasting. To mitigate the problems of the above approaches we formalize CL strategies along the training as well as the training iteration scale. We propose several new curricula, and systematically evaluate their performance in two experimental sets. For our experiments, we utilize six datasets generated from prominent chaotic systems. We found that the newly proposed increasing training scale curricula with a probabilistic iteration scale curriculum consistently outperforms previous training strategies yielding an NRMSE improvement of up to 81% over FR or TF training. For some datasets we additionally observe a reduced number of training iterations. We observed that all models trained with the new curricula yield higher prediction stability allowing for longer prediction horizons.
翻译:以LSTM 和 GRU 为基础的序列到序列模型是预测时间序列数据以达到最新业绩的最受欢迎的选择。 培训这类模型可能很微妙。 这方面的两种最常见的培训战略是教师强迫(TF)和自由运行(FR)。 可以利用TF帮助模型更快地趋同,但可能会由于培训和推断阶段之间的差异而引发接触偏见问题。 FR帮助避免了这一点,但不一定导致更好的结果,因为它往往使培训课程变得缓慢和不稳定。 排定抽样是解决这些问题的第一种方法,从两个世界中选取最佳数据并将其合并为课程学习(CL)战略。 尽管定期抽样似乎可以令人信服地替代FR和FFR。 我们发现,即使精心调整了时间序列预测,排定的抽样可能会导致培训过早结束。 为了缓解上述方法的问题,我们根据培训的数量以及培训的规模将CLF战略正规化,我们提出了几个新的课程,并系统地评价了它们两个实验系列的绩效。 为了不断升级,我们利用先前的学习模式,我们利用了六个数据系统,我们利用了一种不断升级的学习模式,我们利用了一种不断升级的顺序,我们利用了一种最新的学习系统,我们利用了一种不断改进的学习的顺序。