Conformal prediction is a distribution-free technique for establishing valid prediction intervals. Although conventionally people conduct conformal prediction in the output space, this is not the only possibility. In this paper, we propose feature conformal prediction, which extends the scope of conformal prediction to semantic feature spaces by leveraging the inductive bias of deep representation learning. From a theoretical perspective, we demonstrate that feature conformal prediction provably outperforms regular conformal prediction under mild assumptions. Our approach could be combined with not only vanilla conformal prediction, but also other adaptive conformal prediction methods. Experiments on various predictive inference tasks corroborate the efficacy of our method.

翻译：非正式预测是建立有效预测间隔的无分配技术。 虽然通常人们在产出空间进行一致预测,但这并非唯一的可能。 在本文中,我们提出符合特性预测,通过利用深层代表性学习的感应偏差,将符合性预测的范围扩大到语义特征空间。从理论角度看,我们证明符合性预测在轻度假设下比正常的符合性预测好。我们的方法不仅可以结合香草符合性预测,还可以结合其他适应性符合性预测方法。关于各种预测性推断任务的实验证实了我们方法的有效性。