SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors
Abstract
Conformal Prediction (CP) provides robust uncertainty guarantees for predictive models, but is typically applied post hoc, which misaligns model training with the conformal goal of producing efficient (i.e., narrow) intervals. We propose SPACR (Single-Pass Adaptive Conformal Regressor), a novel method for directly training uncertainty-aware regressors within a differentiable loss. SPACR jointly optimizes accuracy, efficiency, and validity without batch-splitting or a predefined confidence level during training. As a result, a single SPACR model yields valid prediction intervals at multiple confidence levels during inference, avoiding the costly retraining required by methods like Directly Optimized Inductive Conformal Regression (DOICR). Experiments on diverse tabular and image datasets show that SPACR consistently gives tighter intervals and better coverage-efficiency trade-offs compared to standard CP and DOICR, while significantly reducing computational costs relative to retraining-dependent baselines.
Related
- CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support
- Adaptive Conformal Redistribution for Inter-class Transitional Uncertainty in Medical Image Classification
- Conformal Uncertainty Quantification Guarantees for Neural Operators
- Adaptive Conformal Inference through the Lens of Blackwell Approachability
- CoCoNet: Convex Conformal Network for Multi-Dimensional Uncertainty Regions
BibTeX
@misc{messoudi2026spacr,
title = {{SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors}},
author = {Soundouss Messoudi and Sylvain Rousseau and Sébastien Destercke},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.10734},
eprint = {2606.10734},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.10734},
}
RIS
TY - UNPB
TI - SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors
AU - Soundouss Messoudi
AU - Sylvain Rousseau
AU - Sébastien Destercke
PY - 2026
DA - 2026/10/28
PB - arXiv
DO - 10.48550/arxiv.2606.10734
UR - https://arxiv.org/abs/2606.10734
AB - Conformal Prediction (CP) provides robust uncertainty guarantees for predictive models, but is typically applied post hoc, which misaligns model training with the conformal goal of producing efficient (i.e., narrow) intervals. We propose SPACR (Single-Pass Adaptive Conformal Regressor), a novel method for directly training uncertainty-aware regressors within a differentiable loss. SPACR jointly optimizes accuracy, efficiency, and validity without batch-splitting or a predefined confidence level during training. As a result, a single SPACR model yields valid prediction intervals at multiple confidence levels during inference, avoiding the costly retraining required by methods like Directly Optimized Inductive Conformal Regression (DOICR). Experiments on diverse tabular and image datasets show that SPACR consistently gives tighter intervals and better coverage-efficiency trade-offs compared to standard CP and DOICR, while significantly reducing computational costs relative to retraining-dependent baselines.
ER -