DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Menadjiev, Enver, Seong, Jihyeon, Yeo, Jisu, Choi, Jaesik
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917550315536384
author Menadjiev, Enver
Seong, Jihyeon
Yeo, Jisu
Choi, Jaesik
author_facet Menadjiev, Enver
Seong, Jihyeon
Yeo, Jisu
Choi, Jaesik
contents Sequential conformal prediction (CP) provides valid uncertainty quantification under the assumption of residual exchangeability. However, this assumption is often violated in real-world time series due to temporal dependencies and distributional shifts. While recent methods attempt to approximate exchangeability through reweighting, identifying optimal weights remains an open challenge. To address this limitation, we propose DistMatch, a binning-based method that recursively partitions residuals within a binary tree using the Kolmogorov-Smirnov (KS) statistic. We theoretically show that this partitioning induces approximately exchangeable leaves, thereby avoiding the need for reweighting. By applying quantile regression with online updates within each leaf, DistMatch enables locally adaptive inference and improves robustness to distributional shifts. Extensive experiments demonstrate that DistMatch outperforms existing sequential CP methods.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00690
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction
Menadjiev, Enver
Seong, Jihyeon
Yeo, Jisu
Choi, Jaesik
Machine Learning
Sequential conformal prediction (CP) provides valid uncertainty quantification under the assumption of residual exchangeability. However, this assumption is often violated in real-world time series due to temporal dependencies and distributional shifts. While recent methods attempt to approximate exchangeability through reweighting, identifying optimal weights remains an open challenge. To address this limitation, we propose DistMatch, a binning-based method that recursively partitions residuals within a binary tree using the Kolmogorov-Smirnov (KS) statistic. We theoretically show that this partitioning induces approximately exchangeable leaves, thereby avoiding the need for reweighting. By applying quantile regression with online updates within each leaf, DistMatch enables locally adaptive inference and improves robustness to distributional shifts. Extensive experiments demonstrate that DistMatch outperforms existing sequential CP methods.
title DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction
topic Machine Learning
url https://arxiv.org/abs/2606.00690