面向概率时间序列预测的MLP超参数调优
Hyperparameter Tuning MLPs for Probabilistic Time Series Forecasting
AI总结：
本研究探究上下文长度、验证策略等时间序列相关超参数对最优MLP预测性能的影响，构建了含97200次评估的最大时间序列预测元数据集TSBench，并验证其在多保真度超参数优化中的效用。
摘要：
时间序列预测旨在通过分析过去的趋势和模式预测未来事件。尽管该领域已有大量研究，但深度学习应用于时间序列预测的某些关键方面仍不明确。本研究主要聚焦于上下文长度、验证策略等与时间序列相关的特定超参数，对当前最优MLP模型在时间序列预测任务中性能的影响。我们开展了全面的系列实验，覆盖20个时间序列预测数据集，每个数据集设置4800种配置，结果证明了调优这些参数的重要性。此外，本文提出了目前规模最大的时间序列预测元数据集TSBench，包含97200次评估，规模是该领域以往研究的20倍。最后，我们验证了所构建的元数据集在多保真度超参数优化任务中的实用性。
英文摘要：
Time series forecasting attempts to predict future events by analyzing past trends and patterns. Although well researched, certain critical aspects pertaining to the use of deep learning in time series forecasting remain ambiguous. Our research primarily focuses on examining the impact of specific hyperparameters related to time series, such as context length and validation strategy, on the performance of the state-of-the-art MLP model in time series forecasting. We have conducted a comprehensive series of experiments involving 4800 configurations per dataset across 20 time series forecasting datasets, and our findings demonstrate the importance of tuning these parameters. Furthermore, in this work, we introduce the largest metadataset for timeseries forecasting to date, named TSBench, comprising 97200 evaluations, which is a twentyfold increase compared to previous works in the field. Finally, we demonstrate the utility of the created metadataset on multi-fidelity hyperparameter optimization tasks.
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。
