Deep Learning predictions with measurable confidence are increasingly desirable for real-world problems, especially in high-risk settings. The Conformal Prediction (CP) framework is a versatile solution that guarantees a maximum error rate given minimal constraints. In this paper, we propose a novel conformal loss function that approximates the traditionally two-step CP approach in a single step. By evaluating and penalising deviations from the stringent expected CP output distribution, a Deep Learning model may learn the direct relationship between the input data and the conformal p-values. We carry out a comprehensive empirical evaluation to show our novel loss function's competitiveness for seven binary and multi-class prediction tasks on five benchmark datasets. On the same datasets, our approach achieves significant training time reductions up to 86% compared to Aggregated Conformal Prediction (ACP), while maintaining comparable approximate validity and predictive efficiency.

翻译：深度学习在具有可测量置信度方面的预测对于现实问题越来越有吸引力，尤其是在高风险场景中。共形预测（CP）框架是一种通用解决方案，能够在最小约束条件下保证最大错误率。本文提出了一种新的共形损失函数，可将传统的两步CP方法近似为单步实现。通过评估和惩罚对严格预期CP输出分布的偏差，深度学习模型可以学习输入数据与共形p值之间的直接关系。我们进行了全面的实证评估，以证明我们提出的损失函数在五个基准数据集的七项二元和多类预测任务中的竞争力。在相同数据集上，与聚合共形预测（ACP）相比，我们的方法训练时间显著减少高达86%，同时保持了可比的近似有效性和预测效率。