Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Rongyi, Sun, Wenguang, Zhao, Zinan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910257720066048
author Sun, Rongyi
Sun, Wenguang
Zhao, Zinan
author_facet Sun, Rongyi
Sun, Wenguang
Zhao, Zinan
contents This paper addresses structured out-of-distribution (OOD) testing in high-stakes machine learning applications. Traditional conformal methods rely on joint exchangeability, making it difficult to incorporate auxiliary information such as spatiotemporal or grouping structures. To overcome this limitation, we propose the structure-adaptive conformal q-value (SCQ), a significance index that integrates individual test evidence with structural patterns. We also develop pseudo-score-guided transductive automated model selection (P-TAMS), which adapts conformalized model selection to structured OOD testing across a toolbox of candidate models. Together, SCQ and P-TAMS form a unified framework under pairwise exchangeability, providing finite-sample error-rate control, improved power, and enhanced interpretability. Experiments on simulated and real data demonstrate that the proposed approach controls the false discovery rate and performs well across diverse settings.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26429
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing
Sun, Rongyi
Sun, Wenguang
Zhao, Zinan
Methodology
Artificial Intelligence
Machine Learning
This paper addresses structured out-of-distribution (OOD) testing in high-stakes machine learning applications. Traditional conformal methods rely on joint exchangeability, making it difficult to incorporate auxiliary information such as spatiotemporal or grouping structures. To overcome this limitation, we propose the structure-adaptive conformal q-value (SCQ), a significance index that integrates individual test evidence with structural patterns. We also develop pseudo-score-guided transductive automated model selection (P-TAMS), which adapts conformalized model selection to structured OOD testing across a toolbox of candidate models. Together, SCQ and P-TAMS form a unified framework under pairwise exchangeability, providing finite-sample error-rate control, improved power, and enhanced interpretability. Experiments on simulated and real data demonstrate that the proposed approach controls the false discovery rate and performs well across diverse settings.
title Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing
topic Methodology
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.26429