arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.08485cs.LG
收藏

时间序列预测的多目标模型选择

Multi-Objective Model Selection for Time Series Forecasting

Technical University of Munich(慕尼黑工业大学);AWS AI Labs(AWS人工智能实验室);Amazon Web Services(亚马逊云科技);Zalando Research(Zalando研究院)

Oliver Borchert, David Salinas, Valentin Flunkert, Tim Januschowski, Stephan Günnemann

摘要:

时间序列预测的研究主要集中在开发提高准确性的方法。然而,其他标准,如训练时间或延迟,在许多现实世界的应用程序中是至关重要的。因此,我们解决的问题,如何选择一个合适的预测模型,为一个给定的数据集之间的过多的可用的预测方法时,准确性只是许多标准之一。为此,我们的贡献是双重的。首先,我们提出了一个全面的基准测试,在44个异构的公开数据集上评估了7种经典和6种深度学习预测方法。基准代码是开源的,所有方法的评估和预测都是开源的。这些评估使我们能够回答一些悬而未决的问题,例如深度学习模型要优于经典模型所需的数据量。其次,我们利用基准评估来学习考虑多个目标(如准确性和延迟)的良好默认值。通过学习从预测模型到性能指标的映射,我们证明了我们的方法PARETOSELECT能够准确地从帕累托前沿选择模型-减轻了训练或评估许多预测模型的需要。据我们所知,PARETOSELECT构成了在多目标设置中学习默认模型的第一种方法。

英文摘要:

Research on time series forecasting has predominantly focused on developing methods that improve accuracy. However, other criteria such as training time or latency are critical in many real-world applications. We therefore address the question of how to choose an appropriate forecasting model for a given dataset among the plethora of available forecasting methods when accuracy is only one of many criteria. For this, our contributions are two-fold. First, we present a comprehensive benchmark, evaluating 7 classical and 6 deep learning forecasting methods on 44 heterogeneous, publicly available datasets. The benchmark code is open-sourced along with evaluations and forecasts for all methods. These evaluations enable us to answer open questions such as the amount of data required for deep learning models to outperform classical ones. Second, we leverage the benchmark evaluations to learn good defaults that consider multiple objectives such as accuracy and latency. By learning a mapping from forecasting models to performance metrics, we show that our method PARETOSELECT is able to accurately select models from the Pareto front -- alleviating the need to train or evaluate many forecasting models for model selection. To the best of our knowledge, PARETOSELECT constitutes the first method to learn default models in a multi-objective setting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑