arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.05060cs.LGmath.STstat.MLstat.TH
收藏

ResCP:用于时间序列预测的水库置信区间预测

ResCP: Reservoir Conformal Prediction for Time Series Forecasting

UiT the Arctic University of Norway(UiT北极大学);IDSIA USI-SUPSI, Università della Svizzera italiana(IDSIA瑞士联合大学);University of Oxford(牛津大学);NORCE Norwegian Research Centre AS(挪威研究机构)

Roberto Neglia, Andrea Cini, Michael M. Bronstein, Filippo Maria Bianchi

AI总结:

ResCP通过水库计算实现无训练时间序列预测的置信区间方法,有效处理局部时间动态并保持计算效率。

摘要:

置信区间预测为构建无分布预测区间提供了强大的框架,适用于可交换数据。现有将置信区间扩展到序列数据的方法依赖于拟合相对复杂的模型以捕捉时间依赖性。然而,这些方法在样本量小时可能失效,且当底层数据分布变化时往往需要昂贵的重新训练。为克服这些限制,我们提出了Reservoir Conformal Prediction(ResCP),一种新的无训练置信区间预测方法用于时间序列。我们的方法利用了水库计算的效率和表示学习能力,动态重新加权置信度分数。具体而言,我们计算水库状态之间的相似度分数,并利用它们在每一步自适应地重新加权观测残差。通过这种方法,ResCP使我们能够在建模误差分布时考虑局部时间动态,而不会影响计算可扩展性。我们证明,在合理假设下,ResCP在渐近条件下实现条件覆盖,并在多种预测任务中实证展示了其有效性。

英文摘要:

Conformal prediction offers a powerful framework for building distribution-free prediction intervals for exchangeable data. Existing methods that extend conformal prediction to sequential data rely on fitting a relatively complex model to capture temporal dependencies. However, these methods can fail if the sample size is small and often require expensive retraining when the underlying data distribution changes. To overcome these limitations, we propose Reservoir Conformal Prediction (ResCP), a novel training-free conformal prediction method for time series. Our approach leverages the efficiency and representation learning capabilities of reservoir computing to dynamically reweight conformity scores. In particular, we compute similarity scores among reservoir states and use them to adaptively reweight the observed residuals at each step. With this approach, ResCP enables us to account for local temporal dynamics when modeling the error distribution without compromising computational scalability. We prove that, under reasonable assumptions, ResCP achieves asymptotic conditional coverage, and we empirically demonstrate its effectiveness across diverse forecasting tasks.

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。

↑