无需重训即可生成更精准的时间序列置信区间。
Feature Fitted Online Conformal Prediction for Deep Time Series Forecasting Model
- 用预训练模型特征构建残差预测器，轻量高效。
- 12个数据集上覆盖率达标且区间更短。
- 适合需要实时不确定性量化的人工智能应用。
时间序列预测在众多应用中至关重要，基于深度学习的点预测模型表现优异。然而实际场景中还需通过在线置信区间量化预测不确定性。现有方法要么需昂贵重训，要么无法充分利用深度模型表征能力，或缺乏理论保证。为此，我们提出一种轻量级分位数预测方法，无需重训即可实现有效覆盖率和更短区间长度。该方法利用预训练点预测模型提取的特征拟合残差预测器，并结合自适应覆盖率控制机制。理论上证明了方法具有渐近覆盖率收敛性，误差界依赖于底层点预测模型的特征质量。在12个数据集上的实验表明，该方法在保持目标覆盖率的同时，置信区间更紧凑。代码、模型与数据集见Github。
原文摘要 · Abstract (English)
Time series forecasting is critical for many applications, where deep learning-based point prediction models have demonstrated strong performance. However, in practical scenarios, there is also a need to quantify predictive uncertainty through online confidence intervals. Existing confidence interval modeling approaches building upon these deep point prediction models suffer from key limitations: they either require costly retraining, fail to fully leverage the representational strengths of deep models, or lack theoretical guarantees. To address these gaps, we propose a lightweight conformal prediction method that provides valid coverage and shorter interval lengths without retraining. Our approach leverages features extracted from pre-trained point prediction models to fit a residual predictor and construct confidence intervals, further enhanced by an adaptive coverage control mechanism. Theoretically, we prove that our method achieves asymptotic coverage convergence, with error bounds dependent on the feature quality of the underlying point prediction model. Experiments on 12 datasets demonstrate that our method delivers tighter confidence intervals while maintaining desired coverage rates. Code, model and dataset in \href{https://github.com/xiannanhuang/FFDCI}{Github}
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。