用于概率时间序列预测的分位数引导扩散模型
Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting
AI总结：
该研究提出Control-TS模型，将预测分位数作为分布控制量引导预训练扩散预测器，在8个基准测试中提升了预测性能，还引入CLPS评估生成未来序列的下游效用。
摘要：
分位数预测可汇总每个未来时间步的不确定性，而扩散预测器则通过采样的未来轨迹来表示不确定性。我们研究了预测分位数如何作为分布控制量用于扩散预测，具体而言，我们探究了分位数整合机制如何影响其引导预训练扩散预测器的有效性。我们发现，在整个去噪网络中应用残差控制可产生最稳定的改进。我们将该方法实例化为Control-TS，该模型在保持预训练骨干网络冻结的同时学习分位数控制通路。在8个基准测试中，Control-TS始终提升了骨干网络的CRPS，取得了与最先进预测模型相当的性能，且在容量匹配的对比中保留了其增益。进一步分析考察了这些增益如何依赖于分位数粒度、预测器选择和预测质量。最后，我们引入了条件线性预测得分（CLPS），该指标通过评估生成未来序列的下游预测效用，补充了分布度量。这些发现共同表明，预测分位数是显式不确定性估计与基于扩散的轨迹生成之间的有效接口。
英文摘要：
Quantile forecasts summarize uncertainty at each future time step, while diffusion forecasters represent it through sampled future trajectories. We study how predicted quantiles can serve as distributional controls for diffusion forecasting. Specifically, we investigate how the mechanism of quantile integration affects its effectiveness in guiding a pretrained diffusion forecaster. We find that residual control throughout the denoising network yields the most consistent improvements. We instantiate this approach as Control-TS, which learns a quantile-control pathway while keeping the pretrained backbone frozen. Across eight benchmarks, Control-TS consistently improves the backbone's CRPS, achieves competitive performance against state-of-the-art forecasting models, and retains its gains in capacity-matched comparisons. Further analyses examine how these gains depend on quantile granularity, predictor choice, and forecast quality. Finally, we introduce the Conditional Linear Predictive Score (CLPS), which complements distributional metrics by evaluating the downstream forecasting utility of generated futures. Together, these findings support predicted quantiles as an effective interface between explicit uncertainty estimates and diffusion-based trajectory generation.
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。
