用神经网络动态调整时间序列预测区间，提升非平稳环境下的准确性与一致性。
Neural Conformal Control for Time Series Forecasting
- 基于多视图数据的端到端神经控制，自适应调整预测覆盖度。
- 在流行病、用电需求等数据上，覆盖率与概率精度显著提升。
- 适合需要高可靠性预测的场景，如医疗、能源调度。
我们提出一种用于时间序列预测的神经网络置信区域方法，可在非平稳环境中增强自适应性。该方法作为神经控制器，旨在实现目标覆盖概率，通过神经网络编码器端到端融合辅助多视图数据以进一步提升适应能力。此外，模型通过引入单调性约束，增强了不同分位数间预测区间的连贯性，并利用相关任务数据提升少样本学习性能。在流行病、电力需求、天气等多个真实数据集上的实验表明，该方法在覆盖率和概率准确性方面均有显著改进，且是唯一同时具备良好校准性与预测区间一致性的方法。
原文摘要 · Abstract (English)
We introduce a neural network conformal prediction method for time series that enhances adaptivity in non-stationary environments. Our approach acts as a neural controller designed to achieve desired target coverage, leveraging auxiliary multi-view data with neural network encoders in an end-to-end manner to further enhance adaptivity. Additionally, our model is designed to enhance the consistency of prediction intervals in different quantiles by integrating monotonicity constraints and leverages data from related tasks to boost few-shot learning performance. Using real-world datasets from epidemics, electric demand, weather, and others, we empirically demonstrate significant improvements in coverage and probabilistic accuracy, and find that our method is the only one that combines good calibration with consistency in prediction intervals.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。