分叉序列：具有降低波动性的统计和计算高效的多步预测
Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility
AI总结：
研究时间序列预测中如何降低预测波动性，核心方法是采用分叉序列神经网络架构设计，好处是通过集成降低波动性、减少梯度方差、提高推理计算效率，在多数据集上验证了该方法能提升准确性并降低预测波动性。
摘要：
虽然准确性是时间序列预测的关键要求，但跨预测创建日期（FCD）的合理预测波动性同样重要。即使是高度准确的模型也可能在FCD之间产生不稳定的修订，破坏信任并扰乱下游决策。为了提高预测修订的波动性，像MQCNN、MQT和SPADE这样的先进模型采用了强大但未充分探索的神经网络架构设计：分叉序列。这种架构设计对所有FCD上的整个时间序列进行联合编码和解码，在一次前向传播中生成整个多步预测网格。本文通过引入量化预测修订中过度波动性的指标，并提供理论和实证分析，对分叉序列设计进行了形式化并推动其更广泛的采用。理论上阐述了分叉序列的三个关键好处：通过集成降低预测波动性；减少梯度方差，提高训练过程的统计效率；提高推理计算效率。在M系列基准上，使用来自M1、M3、M4和旅游竞赛的16个数据集，验证了与基线窗口采样相比，分叉序列的好处。观察到RNN、LSTM、CNN、Transformer和基于状态空间的架构在各数据集上的中位数sCRPS分别提高了46.2%、49.3%、28.6%、24.7%和6.4%。然后表明，对于用分叉序列训练的这些模型，推理期间的预测集成可以将中位数预测波动性分别降低13.2%、13.0%、10.9%、10.2%和11.2%，同时保持准确性。
英文摘要：
While accuracy is a critical requirement for time series forecasting, an equally important desideratum is reasonable forecast volatility across forecast creation dates (FCDs). Even highly accurate models can produce erratic revisions between FCDs, undermining trust and disrupting downstream decision-making. To improve the volatility of forecast revisions, state-of-the-art models like MQCNN, MQT, and SPADE employ a powerful yet underexplored neural network architectural design: forking-sequences. This architectural design jointly encodes and decodes the entire time series across all FCDs, producing an entire multi-horizon forecast grid in a single forward pass. This approach contrasts with conventional neural forecasting methods that process FCDs independently, generating only a single multi-horizon forecast per forward pass. In this work, we formalize the forking-sequences design and motivate its broader adoption by introducing a metric for quantifying excess volatility in forecast revisions and by providing theoretical and empirical analysis. We theoretically motivate three key benefits of forking-sequences: (i) reduced forecast volatility through ensembling; (ii) gradient variance reduction, improving the statistical efficiency of the training procedure; and (iii) improved inference computational efficiency. We validate the benefits of forking-sequences compared to baseline window-sampling on the M-series benchmark, using 16 datasets from the M1, M3, M4, and Tourism competitions. We observe median sCRPS improvements across datasets of 46.2%, 49.3%, 28.6%, 24.7%, and 6.4% for RNN, LSTM, CNN, Transformer, and State Space-based architectures, respectively. We then show that forecast ensembling during inference can reduce median forecast volatility by 13.2%, 13.0%, 10.9%, 10.2%, and 11.2% for these respective models trained with forking-sequences, while maintaining accuracy.
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。
