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 efficiency and validity without batch-splitting or a predefined confidence levels 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 DOICR. Experiments on diverse 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.

翻译：共形预测（CP）为预测模型提供了稳健的不确定性保证，但通常在事后应用，这使得模型训练与产生高效（即窄）区间的共形目标不一致。我们提出SPACR（单遍自适应共形回归器），这是一种新颖方法，能够在可微损失内直接训练不确定性感知回归器。SPACR联合优化了效率与有效性，无需在训练中进行批次分割或预设置信水平。因此，单个SPACR模型在推理时能针对多个置信水平生成有效的预测区间，避免了像DOICR等方法所需的高代价重新训练。在多种数据集上的实验表明，与标准CP和DOICR相比，SPACR始终能提供更紧凑的区间以及更优的覆盖-效率权衡，同时显著降低计算成本。