Online prediction for streaming time series data has practical use for many real-world applications where downstream decisions depend on accurate forecasts for the future. Deployment in dynamic environments requires models to adapt quickly to changing data distributions without overfitting. We propose POLA (Predicting Online by Learning rate Adaptation) to automatically regulate the learning rate of recurrent neural network models to adapt to changing time series patterns across time. POLA meta-learns the learning rate of the stochastic gradient descent (SGD) algorithm by assimilating the prequential or interleaved-test-then-train evaluation scheme for online prediction. We evaluate POLA on two real-world datasets across three commonly-used recurrent neural network models. POLA demonstrates overall comparable or better predictive performance over other online prediction methods.
翻译:在下游决定取决于未来准确预测的情况下,对流时序数据进行在线预测对许多实际应用具有实际用途。在动态环境中的部署要求各种模型迅速适应不断变化的数据分布,而不会过度适应。我们建议POLA(通过学习率适应在线)自动调节经常性神经网络模型的学习率,以适应不同时间不断变化的时间序列模式。POLA元精量算法的学习率,通过模拟预先或间断测试-培训评价计划进行在线预测。我们用三种常用的经常性神经网络模型的两种真实世界数据集评估POLA。POLA与其他在线预测方法相比,显示了总体可比或更好的预测性表现。