Conformal Prediction for Multi-Step Forecasting: Conditional Coverage and Sharp Score Calibration Rates

Abstract

Uncertainty quantification in prediction is a central problem in statistics and machine learning. Conformal prediction provides a flexible approach to constructing prediction sets with valid marginal coverage under exchangeability. In this paper, we investigate conformal prediction for both one-step and multi-step forecasting from a single stationary time series, addressing temporal dependence and the additional challenges of joint prediction across multiple horizons. We propose a kernel-based framework, called Time series Residual Analysis for Calibration with Kernels (TRACK), for estimating conditional quantiles of residual scores and constructing prediction sets from rolling-window forecasters. The framework accommodates heterogeneous uncertainty across horizons and accounts for dependence induced by rolling estimation, while allowing predictor memory and forecast horizons to grow with the sample size. Our finite-sample bounds quantify how temporal dependence and overlapping score windows affect calibration and coverage. We further derive bounds for conditional quantile estimation and pointwise conditional coverage discrepancy. The guarantees extend to more general predictors that admit an accurate rolling-window approximation. We also derive matching minimax bounds over classes of known score maps, clarifying how overlapping score windows affect calibration accuracy. Experimental results from simulations and applications to wind energy generation and bike sharing demand show that our methods improve regional conditional coverage while maintaining competitive interval widths.

Conformal Prediction and Conditional Coverage for Tabular Foundation Models
Sungwoo Park, Sunghee Park, Won Chang
arXiv28 Sep 2026PreprintCC BY 4.0Full textStatisticsarXiv
How Synthetic Labels Improve Conformal Prediction: A Perspective on Conditional Coverage
Qianyi Chen, Bo Li
arXiv27 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
Sharp training-conditional coverage for conformal prediction under covariate shift
Mehrdad Pournaderi
arXiv27 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
Attribution-State Conformal Forecasting: Residual-Independent Explanation States for Uncertainty Calibration Under Distribution Shift
Shiza Riaz Memon, Saad Ahmed Qazi
Mathematics2 Nov 2026Peer-reviewedCC BY 4.0General mathematicsCrossref
Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization
Lingfei Kong
arXiv18 Sep 2026PreprintarXiv licenceFull textBioinformatics & computational biology StatisticsarXiv

Cite

BibTeX RIS

BibTeX

@misc{he2026conformal,
  title = {{Conformal Prediction for Multi-Step Forecasting: Conditional Coverage and Sharp Score Calibration Rates}},
  author = {Siyuan He and Yuhong Yang},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.12004},
  eprint = {2611.12004},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.12004},
}

RIS

TY  - UNPB
TI  - Conformal Prediction for Multi-Step Forecasting: Conditional Coverage and Sharp Score Calibration Rates
AU  - Siyuan He
AU  - Yuhong Yang
PY  - 2026
DA  - 2026/11/09
PB  - arXiv
DO  - 10.48550/arxiv.2611.12004
UR  - https://arxiv.org/abs/2611.12004
AB  - Uncertainty quantification in prediction is a central problem in statistics and machine learning. Conformal prediction provides a flexible approach to constructing prediction sets with valid marginal coverage under exchangeability. In this paper, we investigate conformal prediction for both one-step and multi-step forecasting from a single stationary time series, addressing temporal dependence and the additional challenges of joint prediction across multiple horizons. We propose a kernel-based framework, called Time series Residual Analysis for Calibration with Kernels (TRACK), for estimating conditional quantiles of residual scores and constructing prediction sets from rolling-window forecasters. The framework accommodates heterogeneous uncertainty across horizons and accounts for dependence induced by rolling estimation, while allowing predictor memory and forecast horizons to grow with the sample size. Our finite-sample bounds quantify how temporal dependence and overlapping score windows affect calibration and coverage. We further derive bounds for conditional quantile estimation and pointwise conditional coverage discrepancy. The guarantees extend to more general predictors that admit an accurate rolling-window approximation. We also derive matching minimax bounds over classes of known score maps, clarifying how overlapping score windows affect calibration accuracy. Experimental results from simulations and applications to wind energy generation and bike sharing demand show that our methods improve regional conditional coverage while maintaining competitive interval widths.
ER  -

Abstract

Related

Cite