RDIT: 基于残差的扩散隐式模型用于概率时间序列预测
RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecasting
AI总结：
针对概率时间序列预测中分布建模不佳、训练与评估指标不匹配的问题，提出结合点估计、残差条件扩散与双向Mamba网络的即插即用框架RDIT，理论证明可通过最优标准差最小化CRPS，在8个多变量数据集上取得更优性能与更快推理。
摘要：
概率时间序列预测（Probabilistic Time Series Forecasting, PTSF）在需要准确且具备不确定性感知的预测以支撑决策的领域中发挥着关键作用。然而，现有方法的分布建模效果欠佳，且存在训练指标与评估指标不匹配的问题。令人意外的是，我们发现为一个强点估计器添加零均值高斯噪声（其标准差与该估计器的训练误差相匹配），就能在PTSF任务中取得当前最优性能。在本研究中，我们提出RDIT——一种即插即用框架，它将点估计与基于残差的条件扩散和双向Mamba网络相结合。我们从理论上证明，通过调整至最优标准差可以最小化连续排序概率分数（Continuous Ranked Probability Score, CRPS），并推导了实现分布匹配的算法。在8个多变量数据集上、跨不同预测时长的评估表明，与强基线模型相比，RDIT实现了更低的CRPS、更快的推理速度以及更优的覆盖率。
英文摘要：
Probabilistic Time Series Forecasting (PTSF) plays a critical role in domains requiring accurate and uncertainty-aware predictions for decision-making. However, existing methods offer suboptimal distribution modeling and suffer from a mismatch between training and evaluation metrics. Surprisingly, we found that augmenting a strong point estimator with a zero-mean Gaussian, whose standard deviation matches its training error, can yield state-of-the-art performance in PTSF. In this work, we propose RDIT, a plug-and-play framework that combines point estimation and residual-based conditional diffusion with a bidirectional Mamba network. We theoretically prove that the Continuous Ranked Probability Score (CRPS) can be minimized by adjusting to an optimal standard deviation and then derive algorithms to achieve distribution matching. Evaluations on eight multivariate datasets across varied forecasting horizons demonstrate that RDIT achieves lower CRPS, rapid inference, and improved coverage compared to strong baselines.
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。
